© 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. 11172
    Prev
    Next
    INDEX
    Explanations

    "],"

    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
    我们在
    -0.08
     Theatre
    -0.07
     Tecn
    -0.07
     nella
    -0.07
    _parse
    -0.07
    我和
    -0.06
    🥤
    -0.06
     두
    -0.06
     Nhà
    -0.06
     Utility
    -0.06
    POSITIVE LOGITS
     Pendant
    0.09
     pendant
    0.08
     обраща
    0.07
    ᶢ
    0.07
     coloc
    0.07
    contract
    0.07
     واحد
    0.06
    𡈽
    0.06
    Rent
    0.06
    QT
    0.06
    Activations Density 0.011%

    No Known Activations