© 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. 58008
    Prev
    Next
    INDEX
    Explanations

    constant values and functions

    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
    urement
    -0.08
    WARDS
    -0.08
    erator
    -0.08
    ¤
    -0.08
    æŁ»
    -0.07
    er
    -0.07
    ä¸įåı¯æĢĿè®®
    -0.07
    à¸Ĺะà¹Ģà¸ļียà¸Ļ
    -0.07
    ged
    -0.07
    åĭĩå¾Ģ缴åīį
    -0.07
    POSITIVE LOGITS
    ially
    0.10
    resse
    0.10
    issimo
    0.09
    ized
    0.09
    enance
    0.09
    ainers
    0.09
    reau
    0.09
    aneous
    0.09
    rophe
    0.08
    ised
    0.08
    Activations Density 0.017%

    No Known Activations