© 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. 34496
    Prev
    Next
    INDEX
    Explanations

    programming constructs like 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
    ç¥Ł
    -0.07
    .nodeName
    -0.07
    åĶ®æ¥¼å¤Ħ
    -0.06
    adona
    -0.06
    format
    -0.06
     Pen
    -0.06
    Æł
    -0.06
    ||||
    -0.06
    å¼łå¿Ĺ
    -0.06
    计
    -0.06
    POSITIVE LOGITS
    ÑĥмÑĭ
    0.08
    èĮĥåĽ´ä¸º
    0.08
    serter
    0.08
    -range
    0.07
    çĭ¬ç«ĭ
    0.07
    NSE
    0.07
     NES
    0.07
    èĮĥåĽ´çļĦ
    0.07
    inspace
    0.07
    BOSE
    0.07
    Activations Density 0.009%

    No Known Activations