© 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. 63183
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    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
    好åIJĹ
    -0.07
    da
    -0.07
    _PROTO
    -0.06
    gid
    -0.06
    æĸĻ
    -0.06
    hn
    -0.06
    ptest
    -0.06
    èijĽ
    -0.06
    assin
    -0.06
    بد
    -0.06
    POSITIVE LOGITS
    ®
    0.10
    à¸ģà¹ĩà¸ķาม
    0.08
    å¤įåĪ¶æĪĸ
    0.08
    /he
    0.08
    ä½ķåľ°
    0.08
    alha
    0.08
    çł¥
    0.07
    izeit
    0.07
    elseif
    0.07
    urger
    0.07
    Activations Density 0.033%

    No Known Activations