© 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. 25693
    Prev
    Next
    INDEX
    Explanations

    testing hypotheses

    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
    truct
    -0.08
    åģļèµ·æĿ¥
    -0.08
    cina
    -0.07
    icone
    -0.07
    lette
    -0.07
    ä¸įä¹ħ
    -0.07
    ä¸įçŁ¥éģĵä½ł
    -0.07
     correctly
    -0.07
    adop
    -0.07
    uvo
    -0.07
    POSITIVE LOGITS
     whether
    0.15
    æĺ¯åIJ¦åħ·æľī
    0.14
    æĺ¯åIJ¦ç¬¦åIJĪ
    0.14
    æĺ¯åIJ¦æľī
    0.13
    æĺ¯åIJ¦åŃĺåľ¨
    0.13
    æĺ¯åIJ¦
    0.13
    æĺ¯åIJ¦ä¸İ
    0.13
    æĺ¯åIJ¦åľ¨
    0.12
     apakah
    0.12
    æĺ¯åIJ¦ä¸º
    0.12
    Activations Density 0.337%

    No Known Activations