© 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. 30739
    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
    lijk
    -0.08
    aré
    -0.08
    égor
    -0.08
    zig
    -0.08
    waran
    -0.08
    asher
    -0.07
    elijke
    -0.07
    arith
    -0.07
    czo
    -0.07
    娥
    -0.07
    POSITIVE LOGITS
    çĺª
    0.08
    rama
    0.07
    è¡¥çŁŃæĿ¿
    0.07
    ãĤ¦ãĥĪ
    0.07
    uiten
    0.06
    æŃ¤èµ·å½¼
    0.06
    æµ·é»ĺ
    0.06
    hea
    0.06
    èĢĮ使
    0.06
    ç¾İå¾Ĺ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.