© 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. 37654
    Prev
    Next
    INDEX
    Explanations

    line and column coordinates

    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
    _bridge
    -0.08
    vole
    -0.07
    olla
    -0.07
    yat
    -0.07
    ato
    -0.06
    erry
    -0.06
     HR
    -0.06
     sal
    -0.06
     HS
    -0.06
     vállal
    -0.06
    POSITIVE LOGITS
    åħ³åı£
    0.08
    åįĬæŃ¥
    0.08
    antin
    0.08
    空èĻļ
    0.08
    mlin
    0.07
    rogen
    0.07
    çIJī
    0.07
    空
    0.07
    osting
    0.07
    Van
    0.07
    Activations Density 0.056%

    No Known Activations