© 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. 1688
    Prev
    Next
    INDEX
    Explanations

    ed / em / edith / emer

    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
    erweise
    -0.10
    enticate
    -0.09
    enburg
    -0.07
    ered
    -0.07
    Ñıд
    -0.07
    entifier
    -0.07
    ment
    -0.07
    .
    -0.06
    herent
    -0.06
     fflush
    -0.06
    POSITIVE LOGITS
    à§įষ
    0.11
    à¹ĩà¸Ķ
    0.11
    issä
    0.11
    oard
    0.10
    ulous
    0.10
    Ùij
    0.10
    ablish
    0.10
     wzglÄĻdu
    0.10
    atron
    0.10
    emiah
    0.10
    Activations Density 3.030%

    No Known Activations