© 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. 37767
    Prev
    Next
    INDEX
    Explanations

    RHS, lhs

    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
    åij³åĦ¿
    -0.08
    ä¸Ĭåı£
    -0.07
    andalone
    -0.07
    izia
    -0.07
    uit
    -0.07
    ones
    -0.07
    tesy
    -0.07
    تاب
    -0.07
    Ĩ
    -0.07
    -0.07
    POSITIVE LOGITS
    emente
    0.07
    ãģĺãĤģãģ¦
    0.07
    forth
    0.07
    vasti
    0.07
    elor
    0.07
    à¸Ĥà¸Ńà¸ĩà¸Ħวาม
    0.07
    æĬ¬é«ĺ
    0.07
    uket
    0.07
    estina
    0.07
    uropa
    0.07
    Activations Density 0.001%

    No Known Activations