© 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. 62162
    Prev
    Next
    INDEX
    Explanations

    crossing and intersection

    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
    utto
    -0.08
    duto
    -0.08
     ((__
    -0.08
    Difference
    -0.07
    vale
    -0.07
     pul
    -0.07
    utton
    -0.07
    urga
    -0.07
    è®Ń
    -0.07
     Difference
    -0.07
    POSITIVE LOGITS
     crossing
    0.10
    交åıī
    0.09
    -cross
    0.09
    ç©¿è¶Ĭ
    0.09
     crossings
    0.08
     intersects
    0.08
     intersections
    0.08
    èĽŁ
    0.08
     Crossing
    0.08
    ç©¿è¿ĩ
    0.08
    Activations Density 0.011%

    No Known Activations