© 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. 28131
    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
    åħ¥ç¾¤
    -0.08
    天ä¸ĭ第ä¸Ģ
    -0.08
    anh
    -0.07
    uada
    -0.07
    ITT
    -0.07
     Barra
    -0.07
    ectl
    -0.07
    ç¼ĸåĪ¶
    -0.07
    大å¹ħå¢ŀåĬł
    -0.07
    æľĢåıĹ欢è¿İ
    -0.06
    POSITIVE LOGITS
    ç£
    0.08
    ergus
    0.08
    ampi
    0.07
    æ¯Ķåݻ年
    0.07
    æIJŀ好
    0.07
    åĪĨ许
    0.07
    agerie
    0.07
    HttpStatus
    0.07
    raft
    0.06
    åħ¬åŃIJ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.