© 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. 29230
    Prev
    Next
    INDEX
    Explanations

    parentheses and numbers

    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
    رÙĪØŃ
    -0.07
    éľĸ
    -0.07
    天ä¸ĭ第ä¸Ģ
    -0.06
    egasus
    -0.06
    umbo
    -0.06
    DataType
    -0.06
    ignet
    -0.06
    Complex
    -0.06
    \M
    -0.06
    èĽĭ
    -0.06
    POSITIVE LOGITS
     Pej
    0.07
    ufen
    0.07
    VED
    0.07
    èģĶ
    0.07
     proportional
    0.07
    ibel
    0.07
    ¶ģ
    0.07
     daque
    0.07
    ,{"
    0.07
    leman
    0.07
    Activations Density 0.026%

    No Known Activations