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

    Neuronpedia

    Jacobian LensNEW
    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. 63253
    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
    減少
    -0.07
     ממ
    -0.07
    ሜ
    -0.06
    teen
    -0.06
    领域的
    -0.06
     secure
    -0.06
    .Rec
    -0.06
    ߚ
    -0.06
    עס
    -0.06
    发育
    -0.06
    POSITIVE LOGITS
    whelming
    0.07
     <=>
    0.07
    _placeholder
    0.07
     narration
    0.07
    了半天
    0.07
    olesale
    0.07
     Chiến
    0.07
     deadliest
    0.07
    classmethod
    0.07
    _shutdown
    0.07
    Activations Density 0.630%

    No Known Activations