© 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. 58170
    Prev
    Next
    INDEX
    Explanations

    Wikipedia article or page

    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
    -INF
    -0.08
    å¦ĤåĪĿ
    -0.08
    _letters
    -0.08
    idge
    -0.08
    antes
    -0.08
    ertest
    -0.08
    å¦Ĥå±±
    -0.07
    æ¯Ķè¾ĥä½İ
    -0.07
    ç½®çĸij
    -0.07
    tester
    -0.07
    POSITIVE LOGITS
     Wikipedia
    0.07
    è¯įæĿ¡
    0.07
    éĢŁ
    0.07
    etta
    0.07
     Encyclopedia
    0.07
     page
    0.06
     Accessed
    0.06
     wiki
    0.06
     wikipedia
    0.06
    wikipedia
    0.06
    Activations Density 0.048%

    No Known Activations