© 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. 60007
    Prev
    Next
    INDEX
    Explanations

    similar

    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
    esa
    -0.09
    ument
    -0.09
    edly
    -0.09
    kana
    -0.09
    ÑĥменÑĤ
    -0.09
    eph
    -0.09
    еÑĢи
    -0.08
    ecil
    -0.08
    amenta
    -0.08
    ிறà¯įà®ķ
    -0.08
    POSITIVE LOGITS
    ities
    0.11
    -looking
    0.11
     halnya
    0.10
    maÃŁen
    0.10
    -minded
    0.09
    ledes
    0.09
    ergestellt
    0.09
    -aged
    0.08
    äºİä¸Ģ
    0.08
    度é«ĺ
    0.08
    Activations Density 0.031%

    No Known Activations