© 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. 20138
    Prev
    Next
    INDEX
    Explanations

    code comments and math expressions

    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
    uck
    -0.08
    upp
    -0.07
    uf
    -0.07
    ikt
    -0.07
    -info
    -0.07
    Âł
    -0.07
    uchos
    -0.07
    ysi
    -0.07
    utz
    -0.07
    ottage
    -0.07
    POSITIVE LOGITS
    çī¹åĪ«å£°æĺİ
    0.08
    ä½Ĩæĺ¯ä»ĸ们
    0.07
    zilla
    0.07
    esak
    0.07
    vias
    0.07
    évaluation
    0.07
    CCCCCC
    0.07
    ιαί
    0.07
    çļĦæŶåĢĻåı¯ä»¥
    0.07
    ébastien
    0.07
    Activations Density 0.004%

    No Known Activations