© 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. 15608
    Prev
    Next
    INDEX
    Explanations

    pyrolysis

    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
    sst
    -0.08
    ities
    -0.07
    åĴĮæĸ¹æ³ķ
    -0.07
    ially
    -0.07
    ancy
    -0.07
    ness
    -0.07
    yb
    -0.07
    angled
    -0.07
    egrity
    -0.06
    bearing
    -0.06
    POSITIVE LOGITS
    ัà¸ĩ
    0.09
    ulton
    0.08
    ÐIJÐŀ
    0.08
    ê¹IJ
    0.08
    olated
    0.08
    /rest
    0.08
    aline
    0.08
    ième
    0.08
    lukan
    0.07
    çİĩé«ĺ
    0.07
    Activations Density 0.018%

    No Known Activations