© 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. 10305
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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
    <tool_response>
    -0.09
    oland
    -0.08
    åĪ°ä¸ĭ
    -0.08
    <|im_start|>
    -0.08
    没äºĨ
    -0.07
    鼶鼶
    -0.07
    éķ¿ç©º
    -0.07
    æĢķ
    -0.07
    !',
    -0.07
    pii
    -0.07
    POSITIVE LOGITS
     //
    0.08
    endcode
    0.07
    ``
    0.07
     âĨĴ
    0.06
     ...
    0.06
    ```
    0.06
     =>
    0.06
     âĢ¦
    0.06
     ->
    0.06
    âĢ¦âĢ¦
    0.06
    Activations Density 0.453%

    No Known Activations