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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23851
    Prev
    Next
    INDEX
    Explanations

    Starting

    np_max-act · gemini-2.0-flash

    sentence-opening framing phrases and discourse markers that set context (temporal, concessive, or direct-address leads).

    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
     Baghd
    -0.08
    )`↵
    -0.07
    明朗
    -0.07
    licants
    -0.07
    Import
    -0.07
     Aval
    -0.07
     attained
    -0.07
    _lane
    -0.07
    :list
    -0.07
     distingu
    -0.07
    POSITIVE LOGITS
    simple
    0.07
    景象
    0.07
    Secure
    0.07
     podía
    0.07
    future
    0.06
    ưởng
    0.06
     categoryName
    0.06
    سلوك
    0.06
    走上
    0.06
    커
    0.06
    Activations Density 0.137%

    No Known Activations