© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 85687
    Prev
    Next
    INDEX
    Explanations

    whole

    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
    终身
    -0.09
    arge
    -0.07
     pushed
    -0.07
     quá
    -0.07
     meter
    -0.07
    DM
    -0.07
    ace
    -0.07
     reb
    -0.07
    odo
    -0.07
     AP
    -0.07
    POSITIVE LOGITS
    _features
    0.08
    뉼
    0.07
    derabad
    0.07
     Kia
    0.07
    -Type
    0.06
    妯
    0.06
    ayette
    0.06
    <QString
    0.06
    ᅧ
    0.06
     druż
    0.06
    Activations Density 0.004%

    No Known Activations