© 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. 58662
    Prev
    Next
    INDEX
    Explanations

    programming syntax and operations

    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
    管çIJĨèĥ½åĬĽ
    -0.08
    管好
    -0.08
    obel
    -0.07
    aik
    -0.07
    ombe
    -0.07
    aits
    -0.07
     admis
    -0.07
    -enable
    -0.07
    enne
    -0.07
    çħ§é¡¾å¥½
    -0.07
    POSITIVE LOGITS
    .operator
    0.07
     coerce
    0.07
    ستÙĨ
    0.06
    _stmt
    0.06
     comprehension
    0.06
     pois
    0.06
    æĮĩ
    0.06
     literal
    0.06
     Casting
    0.06
    erosis
    0.06
    Activations Density 0.026%

    No Known Activations