© 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. 22022
    Prev
    Next
    INDEX
    Explanations

    programming keywords and syntax

    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
     Greenwood
    -0.07
    /categories
    -0.07
    plate
    -0.07
    allo
    -0.07
    otic
    -0.07
    å°Ĩèĩªå·±
    -0.07
    gang
    -0.06
    .Tags
    -0.06
    allet
    -0.06
    æĭĶ
    -0.06
    POSITIVE LOGITS
    å°ıåŃIJ
    0.08
    oky
    0.08
    çĪ·
    0.07
    çŃĿ
    0.07
    å¼ķ
    0.07
    åŃ½
    0.07
    rip
    0.06
    ç£IJ
    0.06
    efon
    0.06
     Wolfe
    0.06
    Activations Density 0.198%

    No Known Activations