© 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. 27161
    Prev
    Next
    INDEX
    Explanations

    a following noun or adjective

    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
    uno
    -0.08
    åIJĦæľī
    -0.07
    äºĭå®ľ
    -0.07
    ยà¸Ńà¸Ķ
    -0.07
     candidate
    -0.07
    à¹ĥà¸Ķ
    -0.06
     either
    -0.06
    WithError
    -0.06
    两èĢħ
    -0.06
    ложил
    -0.06
    POSITIVE LOGITS
     tendency
    0.09
    åı¯å¾ª
    0.09
     penchant
    0.09
    endency
    0.08
    teras
    0.08
    æĺİç¡®
    0.08
     been
    0.08
    onti
    0.07
    Been
    0.07
    èĻİ
    0.07
    Activations Density 0.260%

    No Known Activations