© 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. 15-RESID-POST-AA
    6. 77264
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    wj
    -0.07
    umatic
    -0.07
    磹
    -0.07
    雾
    -0.07
     Viet
    -0.07
     sweat
    -0.07
    周围的
    -0.06
    gebung
    -0.06
     underst
    -0.06
     cen
    -0.06
    POSITIVE LOGITS
    Ⓚ
    0.08
    🕒
    0.07
     נוס
    0.07
    ;;
    0.07
    .quote
    0.07
    🐍
    0.07
    _pos
    0.07
    :)];↵
    0.07
    เผยแพร
    0.07
    핥
    0.06
    Activations Density 0.026%

    No Known Activations