© 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. 51403
    Prev
    Next
    INDEX
    Explanations

    integer type casting

    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
    antau
    -0.10
    _profiles
    -0.09
    .parseFloat
    -0.08
    WSC
    -0.08
    æ¼Ĥæµ®
    -0.08
    ä¸įåIJĪæł¼çļĦ
    -0.08
    chw
    -0.07
    profiles
    -0.07
    Profiles
    -0.07
    æĩ¶
    -0.07
    POSITIVE LOGITS
     integer
    0.13
    æķ´æķ°
    0.11
    integer
    0.11
     integers
    0.10
     Integer
    0.10
    Integer
    0.10
    _integer
    0.09
    (integer
    0.09
    egers
    0.09
    .getInteger
    0.09
    Activations Density 0.042%

    No Known Activations