© 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. 4100
    Prev
    Next
    INDEX
    Explanations

    browser issues and updates

    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
    å°ijä¸įäºĨ
    -0.08
    ä¸įåIJĮçļĦæĺ¯
    -0.08
    并ä¸įéļ¾
    -0.08
    ä¸įåı¯èĥ½çļĦ
    -0.08
     abst
    -0.07
    ä¸įçĽ¸ä¿¡
    -0.07
    opedia
    -0.07
    imaan
    -0.07
    áºŃy
    -0.07
    _ZERO
    -0.07
    POSITIVE LOGITS
     inadequate
    0.16
    ä¸į足ä¹ĭå¤Ħ
    0.13
     inade
    0.13
     adequ
    0.12
    ä¸į足
    0.12
     insufficient
    0.12
    åŃĺåľ¨éĹ®é¢ĺ
    0.12
    ä¸į足çļĦ
    0.11
    åŃĺåľ¨çļĦéĹ®é¢ĺ
    0.11
     недоÑģÑĤаÑĤ
    0.11
    Activations Density 0.605%

    No Known Activations