© 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. 50942
    Prev
    Next
    INDEX
    Explanations

    spin

    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
    Ø©
    -0.09
     spia
    -0.09
    aft
    -0.09
    -fashioned
    -0.09
    eenth
    -0.09
    ../../../
    -0.08
    een
    -0.08
    skal
    -0.08
    sWith
    -0.08
    minos
    -0.08
    POSITIVE LOGITS
    uous
    0.09
    ners
    0.08
    è¿Ļä¸ľè¥¿
    0.07
    urious
    0.07
    less
    0.07
    /
    0.07
    è¿Ļä¸ªä¸ľè¥¿
    0.07
    à°¾
    0.06
    lot
    0.06
    odal
    0.06
    Activations Density 0.012%

    No Known Activations