© 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. 27655
    Prev
    Next
    INDEX
    Explanations

    specific format or structure

    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
    StateException
    -0.08
    abus
    -0.08
    ytä
    -0.08
    chern
    -0.08
    _PAIR
    -0.08
    jeni
    -0.08
    çģµæĦŁ
    -0.08
    è·¯ä¸ľ
    -0.08
    änner
    -0.08
    опо
    -0.08
    POSITIVE LOGITS
     Jonas
    0.07
    Binder
    0.06
    寺
    0.06
     bob
    0.06
     bail
    0.06
     Sonne
    0.06
    ierce
    0.06
    tras
    0.06
    ä¸ĢæľĿ
    0.06
     sebanyak
    0.06
    Activations Density 0.003%

    No Known Activations