© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16052
    Prev
    Next
    INDEX
    Explanations

    nothing wrong with

    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
    tui
    -0.08
    urtle
    -0.08
    ungg
    -0.07
    anen
    -0.07
    uga
    -0.07
    é¹ī
    -0.07
    пеÑĩаÑĤ
    -0.07
    åľŁè±ª
    -0.07
    ickers
    -0.07
    éĺĻ
    -0.07
    POSITIVE LOGITS
     legitimate
    0.17
    åIJĪçIJĨ
    0.16
     harmless
    0.15
    åIJĪçIJĨçļĦ
    0.15
    æŃ£å¸¸çļĦ
    0.14
    æĺ¯æŃ£å¸¸çļĦ
    0.14
    åIJĪæ³ķçļĦ
    0.14
    åIJĪæ³ķ
    0.14
    æŃ£å½ĵ
    0.14
     legitimately
    0.14
    Activations Density 0.209%

    No Known Activations