© 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. 17707
    Prev
    Next
    INDEX
    Explanations

    guillotine, weapons, pattern, passing, sugar, Chicken, user

    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
     iepazÄ«Å¡anÄģs
    -0.08
    (EC
    -0.07
    ä¸Ģæ°Ķ
    -0.07
    Ø°
    -0.07
     izman
    -0.07
    engeb
    -0.07
    çĶ¨çľ¼
    -0.07
    ottie
    -0.07
     '~/
    -0.07
    使å®ĥ
    -0.06
    POSITIVE LOGITS
    uai
    0.09
    kau
    0.08
    -free
    0.07
    祸
    0.07
    anter
    0.06
    .splitext
    0.06
    abad
    0.06
    etta
    0.06
    ä¿¡æģ¯åıijå¸ĥ
    0.06
    ÄĽ
    0.06
    Activations Density 0.514%

    No Known Activations