© 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. 3177
    Prev
    Next
    INDEX
    Explanations

    code syntax and programming constructs

    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
    Scrollbar
    -0.07
    åıªè¦ģæľī
    -0.07
    alih
    -0.07
    çĽ¯
    -0.07
    Ł
    -0.07
    æīĽ
    -0.06
    ÙĦاØŃ
    -0.06
    EPROM
    -0.06
    å¿ħé¡»è¦ģæľī
    -0.06
    _nsec
    -0.06
    POSITIVE LOGITS
    纬
    0.09
     context
    0.08
    contexts
    0.08
    context
    0.08
     contex
    0.08
    /context
    0.08
    ç·¯
    0.08
    usser
    0.07
    ç¿°
    0.07
    tempt
    0.07
    Activations Density 0.272%

    No Known Activations