© 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. 57580
    Prev
    Next
    INDEX
    Explanations

    automorphism, isomorphism, probabilities

    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
    edale
    -0.08
    uyer
    -0.08
    avar
    -0.07
    intl
    -0.07
    _pas
    -0.07
    就好åĥı
    -0.07
    icin
    -0.07
    assi
    -0.07
    eyJ
    -0.06
    管çIJĨç±»
    -0.06
    POSITIVE LOGITS
    æĹ¢èĥ½
    0.10
    æĹ¢è¦ģ
    0.09
    缺ä¸Ģä¸įåı¯
    0.08
    æĹ¢æľī
    0.07
    æĹ¢
    0.07
    angkatan
    0.07
    æĹ¢æĺ¯
    0.07
    lek
    0.07
    OST
    0.07
    åħ¼åħ·
    0.07
    Activations Density 0.029%

    No Known Activations