© 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. 15-RESID-POST-AA
    11. 115110
    Prev
    Next
    INDEX
    Explanations

    skim

    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
     `;↵
    -0.07
    voir
    -0.07
    仃
    -0.07
     dost
    -0.07
    蛹
    -0.07
    \Admin
    -0.07
    第一书记
    -0.07
     tel
    -0.07
    -basket
    -0.07
    .ACCESS
    -0.07
    POSITIVE LOGITS
     Lex
    0.07
     gef
    0.07
    碃
    0.07
     hereby
    0.07
    angle
    0.06
     rate
    0.06
     biç
    0.06
     blade
    0.06
    Mean
    0.06
    通风
    0.06
    Activations Density 0.006%

    No Known Activations