© 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. 46808
    Prev
    Next
    INDEX
    Explanations

    rights and principles

    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
    ontre
    -0.08
     Mestre
    -0.08
    è¿Ļç§įè¡Į为
    -0.08
    æĪĸéĢļè¿ĩ
    -0.08
    dling
    -0.07
    nado
    -0.07
    วà¸Ī
    -0.07
    TX
    -0.07
    ETO
    -0.07
    conds
    -0.07
    POSITIVE LOGITS
    åİŁåĪĻ
    0.09
     principle
    0.08
    æĢĿæĥ³çļĦ
    0.07
    æĦıåij³çĿĢ
    0.07
    arity
    0.07
     premise
    0.07
    teness
    0.07
    ensp
    0.07
    è§Ĥ念
    0.07
    çŃīåŁºæľ¬
    0.07
    Activations Density 0.021%

    No Known Activations