© 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. 27907
    Prev
    Next
    INDEX
    Explanations

    constant or static values

    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
    erez
    -0.09
    éĩįçĶŁä¹ĭ
    -0.07
    fel
    -0.07
     Freak
    -0.07
    ä¸ļ绩é¢ĦåijĬ
    -0.07
    etano
    -0.07
    ç¼ĺ
    -0.07
    纶
    -0.07
    书å±ĭ
    -0.07
     Tight
    -0.06
    POSITIVE LOGITS
     throughout
    0.14
    ä¸įåıĺçļĦ
    0.11
    æģĴå®ļ
    0.11
    åľ¨æķ´ä¸ª
    0.10
     Throughout
    0.09
     constant
    0.09
    ä¸įåıĺ
    0.09
    (Constant
    0.09
    /static
    0.08
     Constant
    0.08
    Activations Density 0.012%

    No Known Activations