© 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. 47636
    Prev
    Next
    INDEX
    Explanations

    osteocalcin, osteonectin, or stanozolol

    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
    naire
    -0.09
    eger
    -0.09
    teenth
    -0.09
    elled
    -0.08
    ãģ¾ãģĹãģŁãģĮ
    -0.08
    embr
    -0.08
    embre
    -0.08
    elige
    -0.08
    nil
    -0.08
    ebb
    -0.08
    POSITIVE LOGITS
    owitz
    0.08
    áŁĭ
    0.08
    lec
    0.07
    pone
    0.07
    ر
    0.07
    ogie
    0.07
    SuppressWarnings
    0.07
    ounty
    0.07
    ivism
    0.07
    irectional
    0.07
    Activations Density 0.003%

    No Known Activations