© 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. 16062
    Prev
    Next
    INDEX
    Explanations

    ask questions or for details

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    大åıij
    -0.07
    忽
    -0.07
    ØŃاد
    -0.07
    ä¸įåĩĨ
    -0.07
    è¡Įèĩ³
    -0.07
    olean
    -0.07
    æ¼Ĥ
    -0.07
    ä»»æĦı
    -0.06
    _FINAL
    -0.06
    rove
    -0.06
    POSITIVE LOGITS
    å±ĬæŶ
    0.08
    Expl
    0.08
    åĪ°æŶåĢĻ
    0.08
    izio
    0.08
    éĽ
    0.08
     Expl
    0.07
     expl
    0.07
    å°ĨæĿ¥çļĦ
    0.07
     exploration
    0.07
    expl
    0.07
    Activations Density 0.007%

    No Known Activations