© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 81787
    Prev
    Next
    INDEX
    Explanations

    real

    np_max-act · gemini-2.0-flash

    formal, expository or technical prose with abstract/evaluative wording, derived or hyphenated terms, and connective phrasing that signals explanation or analysis

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nal
    -0.07
    LAG
    -0.07
     allocate
    -0.07
     setUser
    -0.07
     inclined
    -0.07
    <Model
    -0.07
     Pier
    -0.07
    rise
    -0.07
     seized
    -0.07
    峦
    -0.06
    POSITIVE LOGITS
    מעשה
    0.07
    COPE
    0.07
    純
    0.07
    ⊙
    0.07
    ->___
    0.07
    🥩
    0.06
    >()->
    0.06
     WW
    0.06
    _concat
    0.06
    .Protocol
    0.06
    Activations Density 3.453%

    No Known Activations