© 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. 4875
    Prev
    Next
    INDEX
    Explanations

    contextual

    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
    ainya
    -0.07
    dest
    -0.07
    ths
    -0.07
    ha
    -0.07
    thing
    -0.07
    erklärung
    -0.07
    iasi
    -0.07
    à¹Ģลิศ
    -0.07
    å¯Įç¿ģ
    -0.07
    er
    -0.07
    POSITIVE LOGITS
    ual
    0.12
    ually
    0.12
    .TODO
    0.11
    uale
    0.11
    uali
    0.10
    urator
    0.10
    uality
    0.10
    illery
    0.09
    à¸ģารà¸ĵà¹Į
    0.09
    ä¸įæĺİçļĦ
    0.09
    Activations Density 0.027%

    No Known Activations