© 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. 63840
    Prev
    Next
    INDEX
    Explanations

    transverse dimensions, flow, illumination

    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
    çłĶ究æīĢæīĢéķ¿
    -0.09
    åĴ§
    -0.09
    ewed
    -0.08
    дела
    -0.08
    æĪij们è¿ĻäºĽ
    -0.08
    ä¸įå¾ĹäºĨ
    -0.08
    æĪijæĿ¥è¯´
    -0.08
    делÑĭ
    -0.08
    è®©æĽ´å¤ļ
    -0.08
    ÏĨι
    -0.08
    POSITIVE LOGITS
    -
    0.08
     respectively
    0.08
    ↵
    0.07
    ’
    0.07
     presently
    0.07
    c
    0.07
    æĪĸæĺ¯
    0.06
     $
    0.06
     $\
    0.06
    j
    0.06
    Activations Density 0.018%

    No Known Activations