© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50243
    Prev
    Next
    INDEX
    Explanations

    #define directives

    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
    autore
    -0.07
    loh
    -0.07
    azia
    -0.07
     uživ
    -0.07
     apl
    -0.07
    ä¼Łä¸ļ
    -0.07
    .sf
    -0.07
    ä¼łçļĦ
    -0.07
    wl
    -0.07
    proc
    -0.07
    POSITIVE LOGITS
    åIJ¸æĶ¶
    0.09
    rones
    0.08
     absorbing
    0.07
    zil
    0.07
    æŧ
    0.07
    以å¾Ģ
    0.07
    odar
    0.07
    engo
    0.07
    åİŁæĿ¥
    0.07
     pars
    0.07
    Activations Density 0.198%

    No Known Activations