© 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. 37498
    Prev
    Next
    INDEX
    Explanations

    parachute, speed, out, loss

    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
    èĸ°
    -0.08
    udeau
    -0.07
    ÙĬاÙĨ
    -0.07
    ipse
    -0.07
     Habe
    -0.07
    éķľ
    -0.07
    æijĬ
    -0.07
    éŃĶæ³ķ
    -0.07
    иÑĤелÑĮÑģÑĤва
    -0.07
    æĥł
    -0.07
    POSITIVE LOGITS
    åĩıéĢŁ
    0.09
     velocity
    0.09
     speed
    0.09
    çļĦéĢŁåº¦
    0.09
    åĩıç¼ĵ
    0.09
    éĢŁåº¦
    0.09
    arcy
    0.09
    åĬłéĢŁåº¦
    0.08
     slowing
    0.08
    _speed
    0.08
    Activations Density 0.003%

    No Known Activations