© 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. 1940
    Prev
    Next
    INDEX
    Explanations

    points, move, coordinates

    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
    &
    -0.07
    inar
    -0.06
    iento
    -0.06
    -0.06
    ä¸Ģ家
    -0.06
    queeze
    -0.06
    ont
    -0.06
     ware
    -0.06
    ication
    -0.06
    _PARSE
    -0.06
    POSITIVE LOGITS
     glVertex
    0.09
     Points
    0.09
    points
    0.09
     points
    0.09
    POINTS
    0.08
    -corner
    0.08
    koch
    0.08
    Unnamed
    0.08
    ä¸ĭä¸ĢæĿ¡
    0.08
    GED
    0.08
    Activations Density 0.011%

    No Known Activations