© 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. 56014
    Prev
    Next
    INDEX
    Explanations

    invention relates to

    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
    ections
    -0.07
    anen
    -0.07
    ä»ĸåıĪ
    -0.07
    ordes
    -0.06
    éĶĻè§ī
    -0.06
    gtest
    -0.06
    æIJŀ
    -0.06
    åıªæĺ¯ä¸ª
    -0.06
    ignon
    -0.06
    æ¯Ĵ
    -0.06
    POSITIVE LOGITS
     diar
    0.07
    dami
    0.07
    arend
    0.07
    æĺ¾çĦ¶æĺ¯
    0.07
    loom
    0.07
    IBC
    0.07
    Ø®ÙĪر
    0.07
    SEE
    0.07
    æĺİæĹ¥
    0.07
    Ao
    0.06
    Activations Density 0.015%

    No Known Activations