© 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. 47334
    Prev
    Next
    INDEX
    Explanations

    closing tags or markup

    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
    esian
    -0.08
    -front
    -0.07
    éĻ
    -0.07
     )[
    -0.07
    ATAR
    -0.07
     dere
    -0.07
    UNG
    -0.06
    antie
    -0.06
    æĹłåīį
    -0.06
    ardo
    -0.06
    POSITIVE LOGITS
    mitt
    0.08
    spre
    0.07
    è¡Į
    0.07
    æĵĩ
    0.07
    åĪĨè¡Į
    0.07
    gede
    0.07
    æĺĤé¦ĸ
    0.06
    uri
    0.06
    opus
    0.06
    ä¸ĢæĹģ
    0.06
    Activations Density 0.018%

    No Known Activations