© 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. 10133
    Prev
    Next
    INDEX
    Explanations

    code, math, programming, or file paths

    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
    æĩĤ
    -0.06
    —
    -0.06
     Said
    -0.06
    æīįè¡Į
    -0.06
    ger
    -0.06
    -0.05
    imeo
    -0.05
     }.
    -0.05
    åĪĿæģĭ
    -0.05
     Cop
    -0.05
    POSITIVE LOGITS
    ãģ¨ãģĦãģĨãģ®ãģ¯
    0.09
    åįİéĺ³
    0.08
    æģĻ
    0.08
    迪äºļ
    0.08
    "":
    0.08
    -scripts
    0.08
    ”:
    0.08
    âĤ¬âĦ¢
    0.08
    ãģ¨ãģĦãģĨãģĵãģ¨ãģ¯
    0.07
    ught
    0.07
    Activations Density 0.016%

    No Known Activations