© 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. 1292
    Prev
    Next
    INDEX
    Explanations

    every li

    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
    ستا
    -0.06
    asih
    -0.06
    稳ä¸Ń
    -0.06
    ¿
    -0.06
    pron
    -0.06
     symbol
    -0.05
    ffi
    -0.05
    æīĭä¸Ĭ
    -0.05
    ãĤī
    -0.05
    èī¯
    -0.05
    POSITIVE LOGITS
    æ¶īåıĬåĪ°
    0.10
    æ¶īåıĬ
    0.10
    åıijçİ°åľ¨
    0.09
     cặp
    0.09
    .biz
    0.09
    以对
    0.09
    æľīä¸ĭåĪĹ
    0.08
    æ¶īåıĬçļĦ
    0.08
    æľīäººåľ¨
    0.08
    åĽ´ç»ķ
    0.08
    Activations Density 0.167%

    No Known Activations