© 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. 10458
    Prev
    Next
    INDEX
    Explanations

    user prompts and input

    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
     reliably
    -0.07
    Py
    -0.07
    inha
    -0.07
    ä¸įæĺĵ
    -0.06
    ä¾µèļĢ
    -0.06
    Sy
    -0.06
     subscript
    -0.06
    _NOP
    -0.06
    Compiled
    -0.06
    å´ĩæĭľ
    -0.06
    POSITIVE LOGITS
    åį³åı¯å®ĮæĪIJ
    0.09
    å¿ħå¡«
    0.09
     prompted
    0.09
    èµ°å®Į
    0.08
    required
    0.08
    å®ĮæĪIJåIJİ
    0.08
    å®Į
    0.08
     confirmation
    0.08
    å®ĮæĪIJ
    0.08
    å¡«åĨĻ
    0.08
    Activations Density 0.213%

    No Known Activations