© 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. 22164
    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
    çħ§
    -0.07
    lä
    -0.07
    enance
    -0.06
    ergestellt
    -0.06
    ĥģ
    -0.06
    ...\
    -0.06
    åħ¶åľ¨
    -0.06
    ocab
    -0.06
    lers
    -0.06
    _kw
    -0.06
    POSITIVE LOGITS
    -regexp
    0.08
     Wunsch
    0.07
    +%
    0.07
    çݩ转
    0.07
    igg
    0.07
    å¸ĮæľĽèĩªå·±
    0.07
    ä¸įèµ·æĿ¥
    0.07
    æĹ¶èµ·
    0.07
    èĢĮçŁ¥
    0.07
    ä½Ļ份
    0.07
    Activations Density 0.000%

    No Known Activations