© 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. 23790
    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
    å®ŀè·µ
    -0.07
     Cust
    -0.07
    qus
    -0.06
    imest
    -0.06
    asmus
    -0.06
    angel
    -0.06
    è·µ
    -0.06
     Cin
    -0.06
    abh
    -0.06
    å³Ń
    -0.06
    POSITIVE LOGITS
    zion
    0.09
    à®°à¯Ī
    0.07
    èµ°ä¸Ģèµ°
    0.07
    ÙĬاتÙĩ
    0.07
    undo
    0.07
    ivu
    0.07
    æ£ĢæŁ¥ç»Ħ
    0.07
    éļ¾ä¸įæĪIJ
    0.07
    truk
    0.07
    kits
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.