© 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. 23674
    Prev
    Next
    INDEX
    Explanations

    management of

    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
    ãģ£ãģ±
    -0.08
    rome
    -0.08
    aneous
    -0.08
    ़
    -0.08
    pery
    -0.08
    ikov
    -0.08
    ANDOM
    -0.08
    ãĥ¡ãĥ³
    -0.07
    icator
    -0.07
     temu
    -0.07
    POSITIVE LOGITS
    ä¸įåĸĦ
    0.12
    çĿ¬
    0.11
    好èĩªå·±çļĦ
    0.10
    endoza
    0.09
    EDIUM
    0.09
    iddel
    0.09
    ysterious
    0.08
    ikhail
    0.08
    otti
    0.08
    /control
    0.08
    Activations Density 0.057%

    No Known Activations