© 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. 49957
    Prev
    Next
    INDEX
    Explanations

    compare and contrast

    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
     unlike
    -0.07
    ä¸įåĨįæĺ¯
    -0.07
    æĻ®éĢļ
    -0.07
     nonsense
    -0.06
    éĿŀ常æľī
    -0.06
    öz
    -0.06
    æ°¸è¿ľ
    -0.06
    tiny
    -0.06
    ainless
    -0.06
    Minus
    -0.06
    POSITIVE LOGITS
    æĽ´æ³¨éĩį
    0.13
    侧éĩį
    0.12
    侧éĩįäºİ
    0.11
    æĽ´å¤ļåħ³äºİ
    0.10
    æĽ´åĬłæ³¨éĩį
    0.10
    emeld
    0.10
    æĽ´å¤ļçļĦæĺ¯
    0.10
    å¹´å¤ļ
    0.09
    注éĩį
    0.09
    éĩįåľ¨
    0.09
    Activations Density 0.011%

    No Known Activations