© 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. 11401
    Prev
    Next
    INDEX
    Explanations

    atomic and crystal faces

    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
    åĦ¿
    -0.07
    tee
    -0.07
    heit
    -0.07
    åIJ¦
    -0.07
    èĤ¡
    -0.07
    halter
    -0.07
    ste
    -0.06
    éĩ
    -0.06
    ç§ijåѦ
    -0.06
    ÑģÑĮ
    -0.06
    POSITIVE LOGITS
    isson
    0.08
    СÑĤÑĢа
    0.07
    åĴĮ西
    0.07
    0.07
    PLAIN
    0.07
    ãģ¡ãģ¯
    0.07
    ä¹ĭä¸ĭçļĦ
    0.07
    è°ģ家
    0.06
    彬彬
    0.06
    èĵĿåŃĹ
    0.06
    Activations Density 0.001%

    No Known Activations