© 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. 50718
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and names

    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
    -helper
    -0.07
    ูล
    -0.07
    æĴ®
    -0.07
     Zaw
    -0.07
    iette
    -0.07
     Distance
    -0.07
    æı´æľĿ
    -0.07
     inc
    -0.07
    زÙħ
    -0.06
    æİĸ
    -0.06
    POSITIVE LOGITS
    Multiplicity
    0.08
    edis
    0.08
    chemas
    0.07
    Associated
    0.07
     Associated
    0.07
    åĸ
    0.07
    TED
    0.07
    ëł´
    0.07
    èĤ
    0.07
    éĻįèIJ½
    0.07
    Activations Density 0.004%

    No Known Activations