© 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. 33330
    Prev
    Next
    INDEX
    Explanations

    rodents and mice

    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
    shore
    -0.07
     ÑģмÑĭ
    -0.07
    uras
    -0.07
    éħ¸
    -0.07
    ount
    -0.07
    hang
    -0.07
    icara
    -0.07
    宫é¢Īç³ľçĥĤ
    -0.07
    ÑģÑĤе
    -0.07
     اÙĦÙħدر
    -0.07
    POSITIVE LOGITS
    /mac
    0.08
    é¼ł
    0.08
    amac
    0.07
    æ´ŀéĩĮ
    0.07
     fox
    0.07
    hood
    0.07
     hare
    0.07
    é¼
    0.07
    åĩºæ²¡
    0.07
    åIJĪ家
    0.07
    Activations Density 0.132%

    No Known Activations