© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25387
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etta
    -0.07
    夫人
    -0.06
     trat
    -0.06
    ment
    -0.06
    awang
    -0.06
     mw
    -0.06
     order
    -0.06
    ÙĦÙĪ
    -0.06
    els
    -0.06
    imba
    -0.06
    POSITIVE LOGITS
    æľ¬æĸĩéĵ¾æİ¥
    0.08
    नà¥įदà¥įर
    0.08
    urname
    0.08
    heb
    0.08
    /renderer
    0.08
    authentication
    0.08
    гна
    0.08
    _lift
    0.08
    abay
    0.08
     Shack
    0.08
    Activations Density 0.000%

    No Known Activations