© 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. 24822
    Prev
    Next
    INDEX
    Explanations

    distinguish what would help

    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
    oulos
    -0.07
    hini
    -0.07
    人è¯Ħä»·
    -0.07
    ä¹Łæľīä¸ĢäºĽ
    -0.07
    GetObject
    -0.07
     Cib
    -0.07
    ä¹Łæľīå¾Īå¤ļ
    -0.07
     particulars
    -0.06
    å¾ĪåıĹ
    -0.06
    æĺ¯ä¸ĢæīĢ
    -0.06
    POSITIVE LOGITS
    缴æİ¥æĪĸ
    0.08
    æĹ¢èĥ½
    0.08
    åijĹ
    0.08
    缴æİ¥æĪĸéĹ´æİ¥
    0.07
    ìķħ
    0.07
    æľĢèĥ½
    0.07
    æĹ¢åı¯ä»¥
    0.07
    amal
    0.07
    ough
    0.07
    éĩı大
    0.07
    Activations Density 0.016%

    No Known Activations