© 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. 38752
    Prev
    Next
    INDEX
    Explanations

    setting or replacing value

    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
    æīĵåĩº
    -0.07
    ä¸įåıĤåĬł
    -0.07
     basePath
    -0.07
    lap
    -0.07
    å±ħé«ĺä¸įä¸ĭ
    -0.07
    æī
    -0.07
    åįģä½³
    -0.07
    ajah
    -0.07
    æĭ¿åĩºæĿ¥
    -0.07
    åIJįåĪĹ
    -0.07
    POSITIVE LOGITS
    æĸ°çļĦ
    0.13
     replacement
    0.12
     replacements
    0.11
     new
    0.11
    æĽ¿æį¢
    0.11
     REPLACE
    0.11
     replacing
    0.10
     replaces
    0.10
     Replacement
    0.10
    Replacement
    0.10
    Activations Density 0.281%

    No Known Activations