© 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. 51748
    Prev
    Next
    INDEX
    Explanations

    integer and numeric types

    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
    çĶ¨æŶ
    -0.09
    éķ¿çº¦
    -0.08
    bane
    -0.08
    addGroup
    -0.07
    itemName
    -0.07
    aglio
    -0.07
    .maxLength
    -0.07
    tails
    -0.07
    TagName
    -0.07
     //"
    -0.07
    POSITIVE LOGITS
    è¿Ļ个æķ°åŃĹ
    0.12
     numeric
    0.12
    .intValue
    0.11
     integer
    0.11
    æķ´æķ°
    0.11
    .integer
    0.11
    (integer
    0.10
    numeric
    0.10
    integer
    0.10
     numbers
    0.10
    Activations Density 0.514%

    No Known Activations