© 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. 18623
    Prev
    Next
    INDEX
    Explanations

    changes and states

    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
    FACE
    -0.09
    éĽĨåħ¨
    -0.08
    çĶŁåŃIJ女
    -0.08
    пой
    -0.08
    æīĵéĢłæĪIJ为
    -0.08
    ä¸Ĭä¸į
    -0.08
    åĨħçļĦ
    -0.07
    ä¾Ŀä¾Ŀ
    -0.07
    olos
    -0.07
    ÏĥÏħ
    -0.07
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.11
    æ®Ĩå°½
    0.09
    ãģ«ä¼´
    0.09
    äºĨä¸ĢåĪĩ
    0.08
    äºĨä¸ĢåįĬ
    0.07
    带æĿ¥çļĦ
    0.07
    äºĨä¸ĢèĪ¬
    0.07
    å¾Ĺ太
    0.07
    esser
    0.07
    äºĨ对
    0.07
    Activations Density 0.028%

    No Known Activations