© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42241
    Prev
    Next
    INDEX
    Explanations

    probability of letter sequences

    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
    å¿ĺä¸įäºĨ
    -0.06
    .$.
    -0.06
    amerate
    -0.06
    abel
    -0.06
    èĤĿèĥĨ
    -0.06
     natal
    -0.06
    æľīä¸Ģå®ļçļĦ
    -0.06
    opil
    -0.06
    epass
    -0.06
    å«£
    -0.06
    POSITIVE LOGITS
    åįģåŃĹ
    0.08
    ÑĪе
    0.07
     intersection
    0.07
    åħ¬åı¸èĤ¡ä»½
    0.07
    öse
    0.07
    ãĤĩãģĨ
    0.06
    ×Ļ×ķתר
    0.06
    ä¸ĭ载次æķ°
    0.06
    hone
    0.06
    交
    0.06
    Activations Density 0.003%

    No Known Activations