© 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. 58772
    Prev
    Next
    INDEX
    Explanations

    suspected of

    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
     dep
    -0.07
    lada
    -0.07
    rut
    -0.07
     Feinstein
    -0.07
    å¾ĹæĦı
    -0.07
    สัม
    -0.07
    驾
    -0.07
     penned
    -0.06
    -auto
    -0.06
    _host
    -0.06
    POSITIVE LOGITS
    åIJįåī¯
    0.08
    å¯ŀ
    0.07
    iefert
    0.07
    ench
    0.07
    TRACT
    0.07
    chy
    0.07
    -bo
    0.07
    è¹Ī
    0.07
     scrut
    0.07
    èī³éĺ³
    0.07
    Activations Density 0.017%

    No Known Activations