© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 65481
    Prev
    Next
    INDEX
    Explanations

    hoff dot com

    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
    ruc
    -0.08
    ripper
    -0.08
    ï¼ģï¼Ī
    -0.08
    бок
    -0.08
    iknya
    -0.08
    æĿ¥éĻ¢
    -0.08
    èħĭ
    -0.08
     diesmal
    -0.08
    å¼¥éĻĢ
    -0.08
    arer
    -0.08
    POSITIVE LOGITS
    ç¡®å®ŀ
    0.10
    確ãģĭãģ«
    0.09
     indeed
    0.09
     effectivement
    0.08
    確實
    0.07
     memang
    0.07
    ä¹Łç¡®å®ŀ
    0.07
     effettivamente
    0.07
     дейÑģÑĤвиÑĤелÑĮно
    0.07
    æŀľçľŁ
    0.07
    Activations Density 0.010%

    No Known Activations