© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55226
    Prev
    Next
    INDEX
    Explanations

    direction, speed

    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
    noinspection
    -0.09
    ÙĪÙĦØ©
    -0.08
    yle
    -0.07
    olog
    -0.07
     sollen
    -0.07
    //-
    -0.07
    ×ķק
    -0.07
    _RESP
    -0.07
    à¸Ńรà¹Įà¸Ķ
    -0.07
    áĥIJáĥľ
    -0.07
    POSITIVE LOGITS
    eltas
    0.07
    æĸ¹åIJijçļĦ
    0.07
    onne
    0.07
    irection
    0.06
     Vega
    0.06
    arel
    0.06
    akis
    0.06
    imba
    0.06
    ä¸įåIJ¬
    0.06
     Exempl
    0.06
    Activations Density 0.002%

    No Known Activations