© 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. 60167
    Prev
    Next
    INDEX
    Explanations

    would say/get/expect/replace

    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
    好åĥıåľ¨
    -0.07
    æĪijåį´
    -0.07
    æĺ¾çĦ¶
    -0.07
     przecież
    -0.07
    家åĸ»æĪ·æĻĵ
    -0.06
    诲
    -0.06
     viá»ĩn
    -0.06
     supposedly
    -0.06
    è¿ĽæĿ¥
    -0.06
    ×ķ
    -0.06
    POSITIVE LOGITS
    认为æĺ¯
    0.09
    认为
    0.08
    ritz
    0.08
    åłĤåłĤ
    0.08
    åIJijèį£
    0.07
    shaw
    0.07
    noinspection
    0.07
    æĺ§
    0.07
    ļĮ
    0.07
    éĢĢæĪ¿
    0.07
    Activations Density 0.003%

    No Known Activations