© 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. 13314
    Prev
    Next
    INDEX
    Explanations

    jump, discontinuity, impulse, transmission, collision

    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
    ulam
    -0.08
    ymar
    -0.08
    _CHARSET
    -0.08
    è´¡
    -0.07
    fetchAll
    -0.07
    è²¢
    -0.07
    æŬ
    -0.07
    éĤĢæĤ¨
    -0.07
     bland
    -0.07
    ipan
    -0.07
    POSITIVE LOGITS
     discontin
    0.09
    è·³è·ĥ
    0.09
     jump
    0.09
     jumps
    0.08
    çŀ¬éĹ´
    0.07
    è·ĥ
    0.07
    éĹ´æĸŃ
    0.07
    jump
    0.07
    eday
    0.07
    è·¨è¿ĩ
    0.07
    Activations Density 0.003%

    No Known Activations