© 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. 10010
    Prev
    Next
    INDEX
    Explanations

    minimum value or field

    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
    мп
    -0.08
    enzie
    -0.08
    FUL
    -0.08
    å¾ĢæľŁåĽŀ顾
    -0.08
    inheritDoc
    -0.08
    edly
    -0.07
    èµĦ讯ç½ij
    -0.07
    çĺ¾
    -0.07
    ggi
    -0.07
    æ·ĭæ¼ĵ
    -0.07
    POSITIVE LOGITS
    /max
    0.09
    iscal
    0.08
    est
    0.08
    ellaneous
    0.08
     (<
    0.08
    éĶµ
    0.08
    (<
    0.08
    erva
    0.07
    ERENCE
    0.07
    äºĨä¸ĭåİ»
    0.07
    Activations Density 0.036%

    No Known Activations