© 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. 51867
    Prev
    Next
    INDEX
    Explanations

    package

    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
    ä¸ŃåĽ½ç«Ļ
    -0.08
    äºĭå®ŀè¯ģæĺİ
    -0.08
    дже
    -0.08
    éĢļ天
    -0.08
    assa
    -0.08
    äºĮåįģäºĶ
    -0.08
    lix
    -0.08
    estig
    -0.08
     Ñĥви
    -0.08
    cwd
    -0.07
    POSITIVE LOGITS
    å±Ģ
    0.06
    vey
    0.06
    ãĥĹãĥª
    0.06
    oor
    0.06
    rish
    0.06
    çī©
    0.06
     rada
    0.06
    çŀİ
    0.06
     Marc
    0.05
    Marcus
    0.05
    Activations Density 0.016%

    No Known Activations