© 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 EvalsExportsinterp-engineNEWAPI 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. 78144
    Prev
    Next
    INDEX
    Explanations

    Code-related questions/errors

    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
    칩
    -0.07
    完结
    -0.07
     NDEBUG
    -0.07
     한
    -0.06
    ביטוי
    -0.06
    allenge
    -0.06
     tipped
    -0.06
     Lumia
    -0.06
     Smartphone
    -0.06
    ENTION
    -0.06
    POSITIVE LOGITS
     statewide
    0.08
    _ind
    0.07
    Le
    0.07
    coverage
    0.07
    "Our
    0.07
    短期
    0.07
     Gov
    0.07
    _conv
    0.07
    ascular
    0.07
    allows
    0.07
    Activations Density 0.020%

    No Known Activations