© 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. 28383
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    笳
    -0.07
     Bian
    -0.07
    omor
    -0.07
    othi
    -0.07
    ieb
    -0.07
    çł¥
    -0.06
    leder
    -0.06
    ledge
    -0.06
    stance
    -0.06
    -Ta
    -0.06
    POSITIVE LOGITS
    åįķä½į为
    0.09
    .googleapis
    0.08
    åįĺä½į
    0.07
     units
    0.07
    водÑĭ
    0.07
    asa
    0.07
    SelectionMode
    0.07
    apas
    0.07
    หà¸Ļà¹Īวย
    0.07
    ông
    0.07
    Activations Density 0.018%

    No Known Activations