Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 13598
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    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
    首席
    -0.07
     shading
    -0.07
    大会
    -0.07
     glide
    -0.06
    互通
    -0.06
    弧
    -0.06
    _except
    -0.06
    OUSE
    -0.06
    (In
    -0.06
     Strike
    -0.06
    POSITIVE LOGITS
    문화
    0.09
     Pyongyang
    0.08
    مراكز
    0.08
    铄
    0.07
    .border
    0.07
    رؤ
    0.07
    zeń
    0.07
    ۃ
    0.07
     JsonResult
    0.07
     Raqqa
    0.07
    Activations Density 0.034%

    No Known Activations