© 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. 51404
    Prev
    Next
    INDEX
    Explanations

    fully complete

    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
    åħ·æľīä¸Ģå®ļçļĦ
    -0.08
     bỼt
    -0.07
    æľīä¸Ģå®ļçļĦ
    -0.07
    æľīæīĢ
    -0.07
    åįĬå±±
    -0.07
    åħ·æľīä¸Ģå®ļ
    -0.07
    æĺ¯ä¸Ģç§į常è§ģçļĦ
    -0.07
    æľīä¸Ģå®ļ
    -0.06
    Low
    -0.06
    rop
    -0.06
    POSITIVE LOGITS
     fully
    0.11
    åħ¨é¢Ŀ
    0.11
     full
    0.11
    æĺ¯åħ¨
    0.11
    åħ¨è¦ĨçĽĸ
    0.11
     complete
    0.11
    å®Įåħ¨çļĦ
    0.11
     Fully
    0.10
    åħ¨æ¬¾
    0.10
    ä¸įçķĻ
    0.10
    Activations Density 0.070%

    No Known Activations