© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4665
    Prev
    Next
    INDEX
    Explanations

    things to consider

    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
    Negative Logits
     ggf
    -0.07
     (
    -0.07
    æĬĬ
    -0.07
    æĹ¢
    -0.07
    S
    -0.06
    表示
    -0.06
     normally
    -0.06
     later
    -0.06
     arbitrarily
    -0.06
     usual
    -0.06
    POSITIVE LOGITS
    åĢ¼å¾Ĺä¸ĢæıIJçļĦæĺ¯
    0.10
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.10
    éĢīæĭ©éĢĤåIJĪèĩªå·±çļĦ
    0.09
    åĪĨ许
    0.09
    ?>>
    0.09
    并ä¸įæĦıåij³çĿĢ
    0.09
    éļıçĿĢæŶéĹ´çļĦæݨ移
    0.08
    å²ģéĤ£å¹´
    0.08
    ä¹Łä¸įåı¯
    0.08
    ostas
    0.08
    Activations Density 0.026%

    No Known Activations