© 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. 31975
    Prev
    Next
    INDEX
    Explanations

    symmetric group

    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
    æĢ§ä»¥åıĬ
    -0.08
    tesi
    -0.08
    大æ£ĢæŁ¥
    -0.08
    mur
    -0.07
    没æľīåľ¨
    -0.07
    åħ¨éĥ¨éĥ½æĺ¯
    -0.07
    æĢ§åıĬ
    -0.07
    éné
    -0.07
    acap
    -0.07
    niego
    -0.07
    POSITIVE LOGITS
    IPP
    0.07
    æ³
    0.06
    รี
    0.06
    express
    0.06
    éļľ
    0.06
    åĬłè½½ä¸Ń
    0.06
    unk
    0.06
    pons
    0.06
    api
    0.06
    åį¯
    0.06
    Activations Density 0.019%

    No Known Activations