© 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. 40407
    Prev
    Next
    INDEX
    Explanations

    physical locations or parts

    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¸Ńæľī
    -0.06
    åľ¨ç©ºä¸Ń
    -0.06
    owi
    -0.06
    ัà¸Ķ
    -0.06
    akes
    -0.06
    ÑĬÑĤ
    -0.06
    è´¹çĶ¨çĶ±
    -0.06
    çĶŁåľ¨
    -0.06
    ipun
    -0.06
    INU
    -0.06
    POSITIVE LOGITS
    éĺ¿å§Ĩæĸ¯
    0.08
    icola
    0.08
    emps
    0.08
    ÑĩеÑģÑĤве
    0.07
    eração
    0.07
    acon
    0.07
    åĴ²
    0.07
     ÙĪعÙĦÙī
    0.07
    Obsolete
    0.07
    ivan
    0.07
    Activations Density 0.178%

    No Known Activations