© 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. 40097
    Prev
    Next
    INDEX
    Explanations

    code competitions and hackathons

    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
    öv
    -0.07
    åIJĮä¸ļ
    -0.07
    Ĵ
    -0.07
    çĥŃæĴŃ
    -0.07
    è·Łäºº
    -0.06
     ÐļеÑĢ
    -0.06
    é£İä¸Ń
    -0.06
     envel
    -0.06
    åľ¨åİ¿
    -0.06
     emb
    -0.06
    POSITIVE LOGITS
    omen
    0.07
    apt
    0.07
    æĢ
    0.07
     Code
    0.07
     yourselves
    0.07
    udit
    0.07
    ç¨ĭåºı设计
    0.07
    èĦijåĬĽ
    0.07
    ä¼łè¯´ä¸ŃçļĦ
    0.07
     contest
    0.07
    Activations Density 0.036%

    No Known Activations