© 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. 27415
    Prev
    Next
    INDEX
    Explanations

    glycerol

    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
    sWith
    -0.08
    ingi
    -0.07
    uras
    -0.07
    µ
    -0.07
    INGS
    -0.07
    اÙģتÙĩ
    -0.07
    menti
    -0.07
    è¦ģèĬ±
    -0.07
    ymb
    -0.07
    ishi
    -0.07
    POSITIVE LOGITS
    itol
    0.07
    à¹Ģà¸Ľà¸¥à¹Īา
    0.07
    åĦ¿
    0.07
    phone
    0.07
    foreground
    0.06
    igue
    0.06
    bean
    0.06
    -water
    0.06
    wood
    0.06
    Ń
    0.06
    Activations Density 0.034%

    No Known Activations