© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30354
    Prev
    Next
    INDEX
    Explanations

    assigned or obtained values

    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
    odb
    -0.08
    æİ¥åĬĽ
    -0.08
    oment
    -0.07
    éģ¨
    -0.07
    entic
    -0.07
    voz
    -0.07
    znam
    -0.07
    梧
    -0.07
     Incre
    -0.07
    inston
    -0.07
    POSITIVE LOGITS
     obtained
    0.13
     via
    0.10
     obtenido
    0.09
     obtenu
    0.09
    à¸ľà¹Īาà¸Ļà¸ģาร
    0.09
    æĺ¯éĢļè¿ĩ
    0.09
     Obt
    0.09
    via
    0.09
    éĢļè¿ĩ对
    0.09
    obt
    0.08
    Activations Density 0.259%

    No Known Activations