© 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. 33421
    Prev
    Next
    INDEX
    Explanations

    sequence: term of

    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
    ×ķ×ĵ
    -0.07
    kak
    -0.07
    æ¶Īè´¹åĵģ
    -0.07
    æİIJ
    -0.07
     ind
    -0.06
    æĢ§
    -0.06
    çİĭæµ·
    -0.06
    greSQL
    -0.06
    è´ŀ
    -0.06
    åIJijä½ł
    -0.06
    POSITIVE LOGITS
    uv
    0.08
    weet
    0.07
    æİĸ
    0.07
    æĺ¯ä»Ģä¹Īåij¢
    0.07
    isman
    0.07
    æķ°æį®æĺ¾ç¤º
    0.07
    çľ¼åħī
    0.07
    asan
    0.07
    menta
    0.07
    rray
    0.07
    Activations Density 0.009%

    No Known Activations