© 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. 31018
    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
    sia
    -0.08
    ä¿ĿæĬ¤æ³ķ
    -0.08
    åĨĢ
    -0.07
    ecken
    -0.07
     Freien
    -0.07
    óis
    -0.07
    ä¸įä¸ĭ
    -0.07
    ä¸įåIJĥ
    -0.07
    ouis
    -0.07
    æĹħ
    -0.07
    POSITIVE LOGITS
    inals
    0.08
    apore
    0.07
    ewater
    0.07
     Wiz
    0.06
    erei
    0.06
    dna
    0.06
    apur
    0.06
    FY
    0.06
    pdb
    0.06
    xxxxxxxx
    0.06
    Activations Density 0.000%

    No Known Activations