© 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. 41266
    Prev
    Next
    INDEX
    Explanations

    probability or fraction

    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
     Accom
    -0.07
    еÑģÑĤв
    -0.07
    ilea
    -0.07
     Relief
    -0.07
    ahn
    -0.07
    è¶Ĭ
    -0.07
     bất
    -0.07
    Preferred
    -0.06
     unloaded
    -0.06
    å¢ŀ
    -0.06
    POSITIVE LOGITS
     fraction
    0.11
     probability
    0.10
    æ¦Ĥçİĩ
    0.09
    probability
    0.09
    fraction
    0.09
    prob
    0.08
     probabil
    0.08
     Fraction
    0.08
     Bakal
    0.08
    Prob
    0.08
    Activations Density 0.007%

    No Known Activations