© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14175
    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
    æī¬éķ¿
    -0.08
     lùi
    -0.08
    åİ»æĦŁåıĹ
    -0.08
    áŀĽ
    -0.08
    è¿ĩæĹ¥åŃIJ
    -0.07
    teria
    -0.07
    pty
    -0.07
    ël
    -0.07
    éĩij森
    -0.07
    æ´»ä¸ĭåİ»
    -0.07
    POSITIVE LOGITS
    éĢļè¿ĩè¿Ļ次
    0.08
    IfNeeded
    0.07
    æıī
    0.07
    ç¿ģ
    0.07
    çķħéĢļ
    0.06
     Satellite
    0.06
     permanently
    0.06
     Sentry
    0.06
    éĢļè¿ĩæľ¬æ¬¡
    0.06
    à¸ĸ
    0.06
    Activations Density 0.000%

    No Known Activations