© 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. 13742
    Prev
    Next
    INDEX
    Explanations

    name, color, custom, palindromes

    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
    ç¨ĭ
    -0.06
    รุ
    -0.06
    æģ©
    -0.06
    æĽ´åħ¨
    -0.06
     rightly
    -0.06
    Ú©ÙĦ
    -0.06
     undoubtedly
    -0.06
    ugi
    -0.06
    åįģä¸ĥ
    -0.06
    亲临
    -0.06
    POSITIVE LOGITS
    ç²¾å¿ĥ设计
    0.11
     arbitrarily
    0.11
    ç²¾å¿ĥ
    0.10
    æķħæĦı
    0.09
     strategically
    0.09
     carefully
    0.09
    éļıæĦı
    0.09
    ç»ĵæŀĦ设计
    0.09
     desired
    0.09
     Desired
    0.09
    Activations Density 0.004%

    No Known Activations