© 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. 19-RESID-POST-AA
    11. 89427
    Prev
    Next
    INDEX
    Explanations

    scale

    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
    邈
    -0.07
     fundamental
    -0.07
     quasi
    -0.07
     pessim
    -0.06
    重要内容
    -0.06
    🏘
    -0.06
    좋
    -0.06
    (jj
    -0.06
     OnDestroy
    -0.06
    south
    -0.06
    POSITIVE LOGITS
     Biblical
    0.07
     theatrical
    0.07
     displaying
    0.06
     diarrhea
    0.06
    𬶍
    0.06
     no
    0.06
     роли
    0.06
     round
    0.06
    いった
    0.06
    送到
    0.06
    Activations Density 0.000%

    No Known Activations