© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7297
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    ree
    -0.08
    è§īå¾Ĺ
    -0.07
    ensor
    -0.07
    re
    -0.07
    enu
    -0.07
    лиÑĩ
    -0.06
    haar
    -0.06
    æ¯Ķ对
    -0.06
    æĥŃ
    -0.06
    ere
    -0.06
    POSITIVE LOGITS
    furt
    0.08
    ä¹ĺ以
    0.08
    ointment
    0.08
    zano
    0.08
    anker
    0.08
    eload
    0.08
    zicht
    0.08
     jäm
    0.07
    æľ¬å°±
    0.07
    kunde
    0.07
    Activations Density 0.012%

    No Known Activations