© 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. 64877
    Prev
    Next
    INDEX
    Explanations

    Internet Explorer versions

    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
    Contours
    -0.07
    ourcem
    -0.07
    nicz
    -0.07
    亿ç¾İåħĥçļĦ
    -0.07
    éĶĦ
    -0.07
    اسب
    -0.06
    ạng
    -0.06
    æĢ»æ¯Ķ
    -0.06
    å®īåİ¿
    -0.06
    åĢįçļĦ
    -0.06
    POSITIVE LOGITS
    ä¸įèĢģ
    0.08
    iry
    0.07
    ko
    0.07
    piring
    0.07
    åıijå¸ĥäºİ
    0.07
    olla
    0.07
    è«
    0.07
    ustos
    0.07
    bac
    0.07
    åŃĺæ´»
    0.07
    Activations Density 0.188%

    No Known Activations