© 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. 55628
    Prev
    Next
    INDEX
    Explanations

    key-value pairs in data structures

    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
    chia
    -0.07
    åĩ¡æľ¬ç½ij注æĺİ
    -0.07
    å±ĢéĿ¢
    -0.07
    åľ¨æľ¬ç«Ļ
    -0.07
     Lump
    -0.07
    Lorem
    -0.07
    endre
    -0.07
    umph
    -0.07
     Metro
    -0.07
    adin
    -0.07
    POSITIVE LOGITS
    æĪij为
    0.07
    íĥķ
    0.07
    mati
    0.07
    _tF
    0.06
     []).
    0.06
    _ARROW
    0.06
    天涯
    0.06
    iho
    0.06
    efe
    0.06
    клÑĭ
    0.06
    Activations Density 0.005%

    No Known Activations