© 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. 44471
    Prev
    Next
    INDEX
    Explanations

    speed, velocity, changing

    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
    å½ĵ天ä¸ĭåįĪ
    -0.08
     Lavor
    -0.07
    å°ĺ
    -0.07
    spill
    -0.07
    åIJİåį³åı¯
    -0.07
    acr
    -0.07
    eki
    -0.07
    -route
    -0.07
     клик
    -0.07
    ึ
    -0.07
    POSITIVE LOGITS
    ä¸įæĸŃåıĺåĮĸ
    0.10
    忽
    0.10
     continuously
    0.10
     continually
    0.09
    åĬłéĢŁåº¦
    0.09
    arder
    0.08
     changing
    0.08
     intermitt
    0.08
    æŶèĢĮ
    0.08
    Velocity
    0.08
    Activations Density 0.003%

    No Known Activations