© 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. 65278
    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
     ì¶Ķ
    -0.07
    ãģĻãĤī
    -0.07
    pute
    -0.07
    å¼ıçļĦ
    -0.07
    gress
    -0.07
     owing
    -0.07
    éĥ½æĺ¯çĶ¨
    -0.07
    dac
    -0.06
    çļĦäºĭæĥħäºĨ
    -0.06
    å¼ı
    -0.06
    POSITIVE LOGITS
    ergarten
    0.08
    addock
    0.08
    messe
    0.07
    <|box_end|>
    0.07
    âĨĴ
    0.07
    OnChange
    0.07
    akah
    0.07
    ä¸įåı¯æĢķ
    0.07
    оÑģÑĤо
    0.07
     ×ķ×Ĵ
    0.07
    Activations Density 0.029%

    No Known Activations