© 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. 40404
    Prev
    Next
    INDEX
    Explanations

    PDA, RF, MRI, IDE, NFL, DR, ES

    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
    .jd
    -0.07
    imet
    -0.07
    ensed
    -0.06
    è¿Ļ对
    -0.06
    ç»ıæµİæĬĢæľ¯
    -0.06
    ups
    -0.06
    以为
    -0.06
    umm
    -0.06
    vince
    -0.06
    æĪij羣
    -0.06
    POSITIVE LOGITS
    ç®Ģ称
    0.09
    "struct
    0.08
    翼翼
    0.07
    簡稱
    0.07
    alap
    0.07
    aç
    0.07
    onacci
    0.07
    asih
    0.07
    kÄģ
    0.07
    å°Ķåħĭ
    0.07
    Activations Density 0.309%

    No Known Activations