© 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. 8453
    Prev
    Next
    INDEX
    Explanations

    code syntax, variable declarations, methods

    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
    uty
    -0.08
    èĺ
    -0.07
    è¯Ħ
    -0.07
    /problem
    -0.07
    èįī
    -0.06
    erts
    -0.06
     basics
    -0.06
    cati
    -0.06
     ÙħÙĤ
    -0.06
    amp
    -0.06
    POSITIVE LOGITS
    ī
    0.08
    aktan
    0.08
    æĪij们è¿ĺè¦ģ
    0.07
    ÑĩеÑģ
    0.07
    ExecutionContext
    0.07
     Spicer
    0.07
    åħ¶å®ĥåªĴä½ĵ
    0.07
    alaus
    0.07
    oused
    0.07
    mith
    0.07
    Activations Density 0.284%

    No Known Activations