© 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. 2823
    Prev
    Next
    INDEX
    Explanations

    mathematical identity or unit

    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
    ighton
    -0.08
    illers
    -0.08
    ziger
    -0.07
    为å¸Ī
    -0.07
    åħ·æľīè¾ĥé«ĺçļĦ
    -0.07
    æľīæľºä¼ļ
    -0.07
     Sampler
    -0.06
    æľīå¾Ī大çļĦ
    -0.06
    éĩĩæł·
    -0.06
    åħ·æľīå¾Īé«ĺçļĦ
    -0.06
    POSITIVE LOGITS
    åŃĺåľ¨çļĦ
    0.08
    çļĦåŃĺåľ¨
    0.08
    à¹ĥ
    0.07
    对æīĢæľī
    0.07
    _MISSING
    0.07
    åŃĺåľ¨äºİ
    0.07
    exist
    0.07
     pairs
    0.07
    èģĶç³»åľ°åĿĢ
    0.07
     пÑĢиÑģ
    0.07
    Activations Density 0.005%

    No Known Activations