© 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 EvalsExportsAPI 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. 29355
    Prev
    Next
    INDEX
    Explanations

    Code comments

    np_max-act · gemini-2.0-flash

    technical and programming-related content, especially code syntax, data types, identifiers, and structured language constructs across multiple languages

    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
     продук
    -0.08
    _expr
    -0.07
    �
    -0.07
     hero
    -0.07
     Exp
    -0.07
    _of
    -0.07
    🤬
    -0.07
     giải
    -0.07
     appro
    -0.07
     succès
    -0.07
    POSITIVE LOGITS
    atient
    0.08
    eng
    0.08
    Concat
    0.07
    😳
    0.07
    ());↵
    0.07
    ]);↵
    0.07
    ้าย
    0.07
    .LayoutControlItem
    0.07
    iap
    0.07
     NK
    0.07
    Activations Density 45.038%

    No Known Activations