© 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. 12590
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    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
    jd
    -0.08
    æĦıä¹īçļĦ
    -0.07
    heimer
    -0.07
    δά
    -0.07
    çĭ±
    -0.07
    æĦıä¹īä¸Ĭ
    -0.07
    Ủ
    -0.07
    č↵↵
    -0.07
    s
    -0.07
    typings
    -0.07
    POSITIVE LOGITS
    opher
    0.07
    rice
    0.07
    嵩
    0.07
     ÑģÑĤад
    0.06
    ×Ĺ×ķת
    0.06
    ellen
    0.06
    -ie
    0.06
    angka
    0.06
    usan
    0.06
    èĵī
    0.06
    Activations Density 0.094%

    No Known Activations