© 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. 27490
    Prev
    Next
    INDEX
    Explanations

    html tags

    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
    vestig
    -0.08
    ä¸įä¼ij
    -0.08
     Ding
    -0.07
    Ñĸз
    -0.07
    _AS
    -0.07
     Ain
    -0.06
    å¦ĤåĪĿ
    -0.06
    .defineProperty
    -0.06
    auses
    -0.06
    Ñįд
    -0.06
    POSITIVE LOGITS
    æł¡æľ¬
    0.07
    alsa
    0.07
    IGA
    0.07
    ogh
    0.07
    空空
    0.07
    algo
    0.07
    onge
    0.07
    els
    0.07
    ontra
    0.07
    áĢº
    0.07
    Activations Density 0.024%

    No Known Activations