© 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. 22258
    Prev
    Next
    INDEX
    Explanations

    code comments or punctuation

    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
    Õ¹
    -0.07
    TRAS
    -0.07
    öker
    -0.07
    è°ĭåıijå±ķ
    -0.07
    çļĦä¸Ģæĸ¹
    -0.06
     Quer
    -0.06
    ify
    -0.06
    really
    -0.06
    olog
    -0.06
    lex
    -0.06
    POSITIVE LOGITS
    驻马
    0.09
    omatik
    0.07
    aed
    0.07
    еÑĩа
    0.07
    çĻ½æĹ¥
    0.07
    ucha
    0.07
    ãģĸãģ¾
    0.07
     RUR
    0.07
    ìĸ´ìĦľ
    0.07
    RIC
    0.07
    Activations Density 0.445%

    No Known Activations