© 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. 45877
    Prev
    Next
    INDEX
    Explanations

    saying same thing

    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
    ÑĢÑıда
    -0.08
    oggler
    -0.08
    æīĢæľīè¿ĻäºĽ
    -0.08
    ulat
    -0.08
    缸è¾ĥ
    -0.08
     ÑģÑĢавнениÑİ
    -0.08
    ÑĢÑıдка
    -0.08
    æ¯Ķ以å¾Ģ
    -0.08
    俱åħ¨
    -0.08
     slu
    -0.08
    POSITIVE LOGITS
     nhau
    0.08
    å½¼æѤ
    0.08
    å½¼æѤçļĦ
    0.08
    åħ±åIJĮçļĦ
    0.07
    ish
    0.07
     дÑĢÑĥг
    0.06
    åħ±åIJĮ
    0.06
    çŃīåIJĮ
    0.06
    opsy
    0.06
     egym
    0.06
    Activations Density 0.051%

    No Known Activations