© 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. 34769
    Prev
    Next
    INDEX
    Explanations

    .com or pm

    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
    ingss
    -0.07
    æī©å±ķèµĦæĸĻ
    -0.07
    жими
    -0.07
    ifik
    -0.06
    moz
    -0.06
    äºĨäºĭ
    -0.06
    ç®Ĺå¾Ĺä¸Ĭ
    -0.06
    жÑĸ
    -0.06
    IGIN
    -0.06
    ilag
    -0.06
    POSITIVE LOGITS
    rocessing
    0.07
    à°¦à±į
    0.07
    .abs
    0.07
    NU
    0.07
    omm
    0.07
     Mens
    0.07
    管æīĢ
    0.07
    _exc
    0.07
    adol
    0.07
    onn
    0.07
    Activations Density 0.499%

    No Known Activations