© 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. 45851
    Prev
    Next
    INDEX
    Explanations

    function arguments and keywords

    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
    èī¯æľº
    -0.07
    çªģ
    -0.07
    踵
    -0.07
    istra
    -0.07
    æĥ³è¯´
    -0.06
    æĦ¿
    -0.06
    anoi
    -0.06
    combe
    -0.06
    +z
    -0.06
    hle
    -0.06
    POSITIVE LOGITS
    è¦ģä¹Īæĺ¯
    0.12
    å¦Ĥæŀľæĺ¯
    0.11
     either
    0.11
     Either
    0.10
    either
    0.10
     Ø¥Ùħا
    0.09
     entweder
    0.09
    ä¸į管æĺ¯
    0.09
    è¦ģä¹Ī
    0.08
    Either
    0.08
    Activations Density 0.145%

    No Known Activations