© 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. 46168
    Prev
    Next
    INDEX
    Explanations

    explaining or describing information

    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
    andung
    -0.07
    tracts
    -0.07
     afterward
    -0.07
    allis
    -0.07
    zion
    -0.06
    trup
    -0.06
    说äºĨç®Ĺ
    -0.06
    çŃīçĿĢä½ł
    -0.06
     afterwards
    -0.06
    åħ¶ä»ĸ
    -0.06
    POSITIVE LOGITS
    å¦Ĥä½ķéĢļè¿ĩ
    0.07
    ãģĿãĤĵãģª
    0.07
    ä»¥ä¹łè¿ijå¹³
    0.07
     ÑĥпÑĢа
    0.07
    è¿Ļæĸ¹éĿ¢çļĦ
    0.07
     systematically
    0.07
    缮çŀª
    0.07
    åľ¨æ²¡æľī
    0.07
    以æľĢ
    0.07
    以åıĬå¦Ĥä½ķ
    0.07
    Activations Density 2.528%

    No Known Activations