© 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. 47428
    Prev
    Next
    INDEX
    Explanations

    constant pressure/speed/velocity

    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
    alani
    -0.09
    亲身
    -0.08
    ä¸ĩæĸ¹
    -0.07
    erber
    -0.07
     outnumber
    -0.07
    ubyte
    -0.07
    æľī幸
    -0.07
    åħ¬åĪĨ
    -0.07
    æĮ£
    -0.07
     sheds
    -0.07
    POSITIVE LOGITS
    åĽºå®ļ
    0.14
    æģĴå®ļ
    0.14
    åĽºå®ļçļĦ
    0.14
     constant
    0.12
     fixed
    0.12
    åĮĢéĢŁ
    0.12
    constant
    0.12
    Fixed
    0.12
     ثابت
    0.11
     Fixed
    0.11
    Activations Density 0.080%

    No Known Activations