© 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. 58024
    Prev
    Next
    INDEX
    Explanations

    technical environment or simulator concepts

    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
     survives
    -0.07
    riers
    -0.07
    èı²çī¹
    -0.07
    åĢĴä¹Ł
    -0.06
    踪
    -0.06
    reven
    -0.06
    å¾·æĸ¯
    -0.06
     Surv
    -0.06
    çł´
    -0.06
    asiat
    -0.06
    POSITIVE LOGITS
    åIJĮæł·çļĦ
    0.11
    åIJĮæł·
    0.10
    åIJĮæł·æĺ¯
    0.09
     extrapol
    0.09
    åIJĮ樣
    0.08
    çĽ¸ä¼¼çļĦ
    0.08
     بÙĨÙģس
    0.08
    举ä¸Ģåıįä¸ī
    0.08
    .predict
    0.08
    çŃīåħ¶ä»ĸ
    0.08
    Activations Density 0.060%

    No Known Activations