© 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. 11-RESID-POST-AA
    6. 76008
    Prev
    Next
    INDEX
    Explanations

    singleton instance access

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    发现自己
    -0.09
    我不想
    -0.08
    觉得自己
    -0.07
    renched
    -0.07
    而在
    -0.07
    erc
    -0.07
     />
    -0.07
     до
    -0.07
    uspend
    -0.07
    心中的
    -0.07
    POSITIVE LOGITS
     FIG
    0.08
    Ada
    0.07
    //=
    0.07
    כיכ
    0.07
    𓏸
    0.07
     Shuttle
    0.07
     Święt
    0.07
    Datos
    0.07
     �
    0.07
    ráf
    0.07
    Activations Density 0.029%

    No Known Activations