© 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. 42969
    Prev
    Next
    INDEX
    Explanations

    identifying or understanding something clear

    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
    sth
    -0.07
    statt
    -0.07
    kali
    -0.07
    æľīä»Ģä¹Īä¸įåIJĮ
    -0.06
    å±ŀå®ŀ
    -0.06
    个人æĪĸ
    -0.06
    edList
    -0.06
    .vars
    -0.06
    çĿģ
    -0.06
    æĮģè¯ģ
    -0.06
    POSITIVE LOGITS
    å¾Īæ¸ħæ¥ļ
    0.10
    nam
    0.10
    ä¹ŁçŁ¥éģĵ
    0.09
    æĺİç¡®çļĦ
    0.09
     rõ
    0.09
    æĺİç¡®
    0.08
    çŁ£
    0.08
    æĨ¬
    0.08
    æ¸ħæ¥ļ
    0.08
    äºĨåIJĹ
    0.08
    Activations Density 0.334%

    No Known Activations