© 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. 51089
    Prev
    Next
    INDEX
    Explanations

    etc and similar enumerations

    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
    ä¸Ģç§į
    -0.07
    ä¸ĢæĿ¡
    -0.07
    aaaaaaaa
    -0.07
    _xor
    -0.06
    oten
    -0.06
    好ä¸ĢçĤ¹
    -0.06
    çķ¥å¾®
    -0.06
    olutely
    -0.06
    pillar
    -0.06
    (or
    -0.06
    POSITIVE LOGITS
     etc
    0.31
    çŃīçŃī
    0.25
    etc
    0.22
     usw
    0.21
     itp
    0.20
    管çIJĨçŃī
    0.20
    æ´»åĬ¨çŃī
    0.19
    ç±»çŃī
    0.19
    åĽ¾çŃī
    0.19
    è´¹çŃī
    0.19
    Activations Density 0.241%

    No Known Activations