© 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. 24664
    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
    inten
    -0.08
    ç·»
    -0.08
    ultos
    -0.08
    ensp
    -0.08
     Desp
    -0.07
    à¸Ŀ
    -0.07
    eldes
    -0.07
    ä¹ĭ称
    -0.07
    -Allow
    -0.07
    ç»Ī
    -0.07
    POSITIVE LOGITS
    ubar
    0.08
     inputs
    0.08
    ä¸įäºī
    0.07
    веÑģ
    0.07
    _inputs
    0.07
    æĻ¤
    0.07
    iropr
    0.07
    zung
    0.07
     Inputs
    0.07
    jure
    0.06
    Activations Density 0.000%

    No Known Activations