© 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. 64393
    Prev
    Next
    INDEX
    Explanations

    mathematical or factual question starters

    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
    onia
    -0.07
    ä»ĸèĩªå·±çļĦ
    -0.06
    imps
    -0.06
    iev
    -0.06
     MIPS
    -0.06
    ảm
    -0.06
    å°Ķåħĭ
    -0.06
     Bermuda
    -0.06
    è¿ijåľ¨
    -0.06
     DPI
    -0.06
    POSITIVE LOGITS
    çļĦçIJĨçĶ±
    0.09
    arkan
    0.08
    strar
    0.08
    å®Ĺ
    0.07
    çIJĨçĶ±ãģ¯
    0.07
    мÑĥÑĢ
    0.07
    uld
    0.07
     Gelegenheit
    0.07
    rix
    0.07
    _argument
    0.07
    Activations Density 0.003%

    No Known Activations