© 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. 26321
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and inverse calculation

    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
    ernals
    -0.07
    osse
    -0.06
    为åIJį
    -0.06
    Require
    -0.06
     ade
    -0.06
     ma
    -0.06
     pit
    -0.06
    terr
    -0.06
    redo
    -0.06
     nominate
    -0.06
    POSITIVE LOGITS
    inger
    0.09
    INGER
    0.08
    iver
    0.08
     Ving
    0.08
    issan
    0.08
    æ¥ĵ
    0.08
    baugh
    0.08
    å¨ģæĸ¯
    0.07
    Clipboard
    0.07
    IFT
    0.07
    Activations Density 0.005%

    No Known Activations