© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 70088
    Prev
    Next
    INDEX
    Explanations

    presentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .prof
    -0.08
    拜师学
    -0.07
     المتعل
    -0.07
    安检
    -0.07
    تحض
    -0.07
    ubectl
    -0.07
    蒋介
    -0.07
     مجر
    -0.07
    ᨕ
    -0.07
     зуб
    -0.07
    POSITIVE LOGITS
    iami
    0.08
     Ay
    0.07
     ui
    0.07
     Que
    0.07
     sw
    0.07
    城堡
    0.07
    _py
    0.07
    _fk
    0.07
    .xlsx
    0.07
    含义
    0.06
    Activations Density 0.000%

    No Known Activations