© 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. 43839
    Prev
    Next
    INDEX
    Explanations

    ask to give

    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
    åºĶéĤĢ
    -0.08
    被认为
    -0.08
    éľĢè¦ģåıĬæŶ
    -0.07
    æĮĩæľĽ
    -0.07
    æĥ³æī¾
    -0.07
    å¾Ĺèµ·
    -0.07
    åIJ¬åıĸäºĨ
    -0.07
    -placeholder
    -0.07
    è·ijåİ»
    -0.06
    ebab
    -0.06
    POSITIVE LOGITS
    尽快
    0.09
    å°½åı¯èĥ½
    0.09
     möglichst
    0.09
    å°½åı¯èĥ½çļĦ
    0.09
    èĩªå·±åİ»
    0.09
    ä¸įè¦ģåĨį
    0.09
    æĿ¥åģļ
    0.08
    ä¸įè¦ģæĬĬ
    0.08
    adak
    0.08
    æľīæĿ¡ä»¶çļĦ
    0.08
    Activations Density 0.241%

    No Known Activations