© 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. 54974
    Prev
    Next
    INDEX
    Explanations

    time signature

    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
    ìķ¼
    -0.07
    沸
    -0.07
     Plain
    -0.06
    ologna
    -0.06
    itarian
    -0.06
     slags
    -0.06
    alay
    -0.06
    .gnu
    -0.06
     plain
    -0.06
    agerie
    -0.06
    POSITIVE LOGITS
    eres
    0.08
    çĽ¸çº¦
    0.08
    zol
    0.08
    .pixel
    0.08
    empa
    0.08
    erd
    0.07
    essin
    0.07
    级以ä¸Ĭ
    0.07
    çī¹çº§
    0.07
    opan
    0.07
    Activations Density 0.002%

    No Known Activations