© 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. 58816
    Prev
    Next
    INDEX
    Explanations

    kinetics and rate measurements

    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
     lifted
    -0.09
    æľ¨é©¬
    -0.08
    åĸ·åļı
    -0.08
    åĪĽæĬķ
    -0.07
     Trusted
    -0.07
     gesture
    -0.07
     stripped
    -0.07
    æŀ¶è®¾
    -0.07
    被åħ³éĹŃ
    -0.07
    semb
    -0.07
    POSITIVE LOGITS
     kinetics
    0.09
    éĢŁçİĩ
    0.08
    (rate
    0.07
    æŀī
    0.07
     Rate
    0.07
     polym
    0.06
    åĽĽçº§
    0.06
    çĶĺéľ²
    0.06
     timers
    0.06
     rate
    0.06
    Activations Density 0.001%

    No Known Activations