© 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. 33265
    Prev
    Next
    INDEX
    Explanations

    words to the left

    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
    usercontent
    -0.09
    asper
    -0.07
    åįĹå®ī
    -0.07
    _SZ
    -0.07
    _tokenize
    -0.07
    γο
    -0.07
    InitialState
    -0.07
    à±
    -0.07
    waan
    -0.07
    store
    -0.07
    POSITIVE LOGITS
    SID
    0.08
     SID
    0.07
    Ctrl
    0.07
    æ¶ĪåĮĸåIJ¸æĶ¶
    0.07
    ito
    0.06
    ç»ıæµİ
    0.06
    ستاÙĨ
    0.06
     Critical
    0.06
    æļ´
    0.06
    æĨİ
    0.06
    Activations Density 0.368%

    No Known Activations