© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59814
    Prev
    Next
    INDEX
    Explanations

    technical software development

    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
    Negative Logits
    jš
    -0.07
    RIX
    -0.07
    atora
    -0.07
    loge
    -0.06
    ret
    -0.06
    为满足
    -0.06
    顾åIJįæĢĿä¹ī
    -0.06
    lij
    -0.06
    k
    -0.06
    set
    -0.06
    POSITIVE LOGITS
    -ish
    0.08
    æıĥ
    0.08
    çĸļ
    0.08
    Convertible
    0.07
    Executing
    0.07
    acruz
    0.07
    inken
    0.07
     kÃŃs
    0.07
    à¸Ķà¹īวยà¸ģัà¸Ļ
    0.07
    åľ¨å½ĵåľ°
    0.07
    Activations Density 0.042%

    No Known Activations