© 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. 26617
    Prev
    Next
    INDEX
    Explanations

    code keywords and directives

    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
    esor
    -0.08
    족
    -0.08
    occhi
    -0.07
    uken
    -0.07
    çļĦåIJĮ
    -0.07
    inerary
    -0.07
    esses
    -0.07
    ä¸įåı¯æĬĹ
    -0.07
    çŃ
    -0.07
    forth
    -0.07
    POSITIVE LOGITS
    ép
    0.09
    åħ¶ä¹IJ
    0.07
    ä¸ĢåĽ¾
    0.06
    åĩĮ天
    0.06
    axes
    0.06
    Ł
    0.06
    _HIDE
    0.06
    ר×ļ
    0.06
    .Suppress
    0.06
    å·´åħĭ
    0.06
    Activations Density 0.002%

    No Known Activations