© 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. 1779
    Prev
    Next
    INDEX
    Explanations

    name or id attributes

    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
    ä¸į认è¯Ĩ
    -0.06
    ä¸Ģå¼łå¼ł
    -0.06
    ripe
    -0.06
    饲
    -0.06
    鸳
    -0.06
    æ¬łç¼´
    -0.06
    æĶ¶ç¼´
    -0.06
    ä¸įåħ¨
    -0.06
    åıĸå¾ĹçļĦæĪIJ绩
    -0.06
    åħ¨éĥ¨éĥ½æĺ¯
    -0.06
    POSITIVE LOGITS
    åIJį称
    0.13
    åij½åIJį为
    0.13
     name
    0.12
    åIJį为
    0.12
    åIJįåŃĹ
    0.12
    åIJį
    0.12
    name
    0.11
    åIJįçĤº
    0.11
    çļĦåIJįåŃĹ
    0.11
    çļĦåIJį称
    0.11
    Activations Density 0.300%

    No Known Activations