© 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. 7962
    Prev
    Next
    INDEX
    Explanations

    col-md, col-sm, col-lg

    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
    ãĥ³
    -0.09
    psilon
    -0.08
    embl
    -0.08
    elsen
    -0.07
    ÑĨÑĥз
    -0.07
    쪽ìĹIJ
    -0.07
    তà§ĩ
    -0.06
    аем
    -0.06
    件å¥Ĺ
    -0.06
    ers
    -0.06
    POSITIVE LOGITS
    arity
    0.11
    iseum
    0.11
    ameleon
    0.10
    apult
    0.09
    ordinates
    0.09
    ombo
    0.09
    ogne
    0.09
     ìĿ¸íķ´
    0.09
    ITICAL
    0.09
    adena
    0.09
    Activations Density 0.029%

    No Known Activations