© 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. 22364
    Prev
    Next
    INDEX
    Explanations

    merchandise, art, ware, kit, debris

    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
    (s
    -0.10
    sWith
    -0.10
    们çļĦ
    -0.09
    ãĤºãģ®
    -0.08
    Õ¶Õ¥ÖĢÕ«
    -0.08
    shal
    -0.08
    ãĤº
    -0.07
    ally
    -0.07
    Ñıми
    -0.07
    æĪĸå¤ļ个
    -0.07
    POSITIVE LOGITS
    اء
    0.09
    ience
    0.09
    沫
    0.08
    awan
    0.08
    undry
    0.08
    estad
    0.07
    uket
    0.07
    isl
    0.07
    æ½¢
    0.07
    åIJĦéķĩ
    0.07
    Activations Density 1.567%

    No Known Activations