© 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. 25691
    Prev
    Next
    INDEX
    Explanations

    levels or structure

    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
    详æĥħ
    -0.08
     détail
    -0.08
    éķ¿çŁŃ
    -0.07
    dong
    -0.07
    Ñıн
    -0.07
    èĬĻ
    -0.07
    hani
    -0.06
    æĥħæľī
    -0.06
    FillColor
    -0.06
    PLUGIN
    -0.06
    POSITIVE LOGITS
     overarching
    0.11
    -level
    0.10
    å±ĤéĿ¢çļĦ
    0.10
     enclosing
    0.09
    级çļĦ
    0.09
    -Level
    0.09
    级
    0.09
    /global
    0.08
    ç´ļçļĦ
    0.08
     meta
    0.08
    Activations Density 0.056%

    No Known Activations