© 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. 38067
    Prev
    Next
    INDEX
    Explanations

    for loops

    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
    被人
    -0.07
    hic
    -0.07
     Frei
    -0.06
    åĵº
    -0.06
    (bbox
    -0.06
    æŁ»
    -0.06
    definitions
    -0.06
    emar
    -0.06
     Schwer
    -0.06
     conversions
    -0.06
    POSITIVE LOGITS
    ataire
    0.08
    urge
    0.07
    atakan
    0.07
    ktes
    0.07
     Larson
    0.07
    åľ¨æł¡åĽŃ
    0.07
    æĸ°åŁİ
    0.07
    orns
    0.07
    edith
    0.07
    .iter
    0.07
    Activations Density 0.098%

    No Known Activations