© 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. 10575
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and formatting

    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
    çŁ
    -0.08
    çĽ¸ä¼¼æĸĩçĮ®
    -0.08
    转载请注æĺİåĩºå¤Ħ
    -0.08
    essian
    -0.08
    ambre
    -0.07
    âncias
    -0.07
    åľ°ä¸»
    -0.07
    cire
    -0.07
     ÙħÙĪÙĤع
    -0.07
    缸åħ³æ³ķå¾ĭ责任
    -0.07
    POSITIVE LOGITS
    uper
    0.07
    _dept
    0.06
     vo
    0.06
    æĪı
    0.06
    oger
    0.06
    uber
    0.06
    æĪ²
    0.06
    æŃĮè¿·
    0.06
    åĭĺå¯Ł
    0.06
    ¶
    0.06
    Activations Density 0.154%

    No Known Activations