© 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. 11-RESID-POST-AA
    11. 23286
    Prev
    Next
    INDEX
    Explanations

    exactly

    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
     richer
    -0.07
     posted
    -0.06
    再到
    -0.06
     ischem
    -0.06
    _missing
    -0.06
     deported
    -0.06
    互通
    -0.06
    责任制
    -0.06
     Asi
    -0.06
     Komm
    -0.06
    POSITIVE LOGITS
    Documentation
    0.08
    irtual
    0.08
    SCRI
    0.08
    .NEW
    0.07
    גל
    0.07
    _PROJECT
    0.07
    .Count
    0.07
    _pars
    0.07
    loads
    0.07
    InlineData
    0.07
    Activations Density 0.005%

    No Known Activations