© 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. 629
    Prev
    Next
    INDEX
    Explanations

    amplifier

    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
    åıªèĥ½éĢļè¿ĩ
    -0.08
    ä¿±è¿Ľ
    -0.08
     اÙĦاص
    -0.08
    ä¸įæ¸Ŀ
    -0.07
    ä¸ĩå¥Ĺ
    -0.07
    è¡Įäºĭ
    -0.07
    Joint
    -0.07
     dispro
    -0.06
    æıIJ示信æģ¯
    -0.06
    isman
    -0.06
    POSITIVE LOGITS
     ampl
    0.09
     amplifier
    0.09
    æĶ¾å¤§
    0.09
     Ampl
    0.08
    æŀ¶æŀĦ
    0.08
    æİ¥åĬĽ
    0.08
    æĶ¾å¤§åĻ¨
    0.08
    çŃīä¸ĵä¸ļ
    0.07
     amplify
    0.07
    èıĬèĬ±
    0.07
    Activations Density 0.040%

    No Known Activations