© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16981
    Prev
    Next
    INDEX
    Explanations

    isms

    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
    ossi
    -0.07
    à§įড
    -0.07
    teen
    -0.07
    aghan
    -0.07
    itional
    -0.07
    ivable
    -0.07
    haul
    -0.07
    ané
    -0.07
    HandlerContext
    -0.07
    æĹłæķħ
    -0.07
    POSITIVE LOGITS
    -leaning
    0.09
    zcze
    0.08
    ically
    0.08
    ÑĥÑİÑī
    0.08
    ituto
    0.07
    ÒĽÐ°
    0.07
    -lite
    0.07
    upport
    0.07
    à¹Į
    0.07
     entirety
    0.07
    Activations Density 0.084%

    No Known Activations