© 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. 41454
    Prev
    Next
    INDEX
    Explanations

    volume capacity

    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
    schap
    -0.07
    ikli
    -0.07
    ydd
    -0.07
    ocu
    -0.07
    ematic
    -0.07
    ritel
    -0.07
    ä¸įæĥĬ
    -0.07
    heus
    -0.07
     плаÑĤежа
    -0.07
    lijke
    -0.07
    POSITIVE LOGITS
    abyrin
    0.09
    containers
    0.08
    AYOUT
    0.08
    ighthouse
    0.08
    andon
    0.07
    ankan
    0.07
    izard
    0.07
    ONDON
    0.07
    izens
    0.07
     thereof
    0.07
    Activations Density 0.006%

    No Known Activations