© 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. 77426
    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
     correctamente
    -0.07
    [J
    -0.07
    -new
    -0.07
    forces
    -0.07
    _floor
    -0.07
    Vs
    -0.06
     Draws
    -0.06
    èmes
    -0.06
    ທ
    -0.06
    _pr
    -0.06
    POSITIVE LOGITS
    Activ
    0.07
     Negot
    0.07
    DataType
    0.07
     factura
    0.07
    \',
    0.07
     UInt
    0.06
     unpredict
    0.06
     neg
    0.06
     Ub
    0.06
    .setIcon
    0.06
    Activations Density 0.002%

    No Known Activations