© 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. 60405
    Prev
    Next
    INDEX
    Explanations

    never

    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
    ä¸įä»ħè¦ģ
    -0.07
    ä¸į论
    -0.07
    ä¸įéľĢ
    -0.07
    é«ĺ人
    -0.07
    ä¸įéĹ®
    -0.07
    åıªè¦ģæľī
    -0.07
    åıªè¦ģæĺ¯
    -0.06
    èĭ¥æĹł
    -0.06
    ÑĤаÑĢи
    -0.06
    ä¸įåĪĨ
    -0.06
    POSITIVE LOGITS
     nowhere
    0.11
     neither
    0.11
    ä¸ĢèĪ¬ä¸įä¼ļ
    0.11
     ÑĢазве
    0.10
    éĥ½ä¸įåı¯èĥ½
    0.10
     вÑĢÑıд
    0.10
     unlikely
    0.09
    缮åīį没æľī
    0.09
     nope
    0.09
     Neither
    0.09
    Activations Density 0.087%

    No Known Activations