© 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. 51994
    Prev
    Next
    INDEX
    Explanations

    boolean type

    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
    Negative Logits
    issage
    -0.08
    emean
    -0.08
    лÑĭм
    -0.07
    apul
    -0.07
    ingan
    -0.07
    ÅĪ
    -0.07
    /down
    -0.07
    /out
    -0.07
    ropolis
    -0.07
    éĴµ
    -0.07
    POSITIVE LOGITS
    Ø·Ùħ
    0.08
    éen
    0.08
    oader
    0.07
    Flip
    0.07
    .flip
    0.07
    mith
    0.06
    ìį¨
    0.06
    ife
    0.06
    -headed
    0.06
    rå
    0.06
    Activations Density 0.065%

    No Known Activations