© 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. 4038
    Prev
    Next
    INDEX
    Explanations

    remain

    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
    è¿ĺä¸į
    -0.07
     omitted
    -0.07
    èİ«è¿ĩäºİ
    -0.07
    reur
    -0.07
     коÑĤоÑĢого
    -0.06
    lude
    -0.06
     alike
    -0.06
     indeed
    -0.06
    æł¹æľ¬ä¸įæĺ¯
    -0.06
    æĢ¥äºİ
    -0.06
    POSITIVE LOGITS
     unchanged
    0.13
    ä¸įåıĺ
    0.13
    继ç»Ń
    0.13
     tetap
    0.12
    继ç»Ńè¿Ľè¡Į
    0.12
     intact
    0.12
    继ç»Ńåľ¨
    0.11
    ä¸įåıĺçļĦ
    0.11
    ç¹¼çºĮ
    0.11
    åİŁæľīçļĦ
    0.11
    Activations Density 0.198%

    No Known Activations