© 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. 33631
    Prev
    Next
    INDEX
    Explanations

    second smallest, victory

    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
    ç¥ŀé¾Ļ
    -0.07
     Heard
    -0.06
    ä¸įä¸ĭ
    -0.06
     w
    -0.06
     jed
    -0.06
     chin
    -0.06
     moz
    -0.06
    å¤§åľ£
    -0.06
    esc
    -0.06
     gross
    -0.06
    POSITIVE LOGITS
    ãģĵãģ¡ãĤīãĤĤ
    0.12
    Again
    0.11
    again
    0.11
     again
    0.10
     Again
    0.10
    ãģĵãĤĮãĤĤ
    0.10
    åıĪæĺ¯ä¸Ģ个
    0.09
     novamente
    0.09
    åıĪæĺ¯
    0.08
    à¸Ńีà¸ģà¸Ħรัà¹īà¸ĩ
    0.08
    Activations Density 0.004%

    No Known Activations