© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15792
    Prev
    Next
    INDEX
    Explanations

    speed and velocity

    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
    ullen
    -0.08
    ÙĨØ©
    -0.07
     lit
    -0.07
    ä¾Ľçµ¦
    -0.07
    ãĥŃãĥ¼ãĥī
    -0.07
     containing
    -0.07
    åľ¨çº¿éĺħ读
    -0.07
    -log
    -0.07
     Dispos
    -0.06
    åݦéĹ¨å¤§åѦ
    -0.06
    POSITIVE LOGITS
    åħīéĢŁ
    0.09
     speeds
    0.09
    éĢŁåº¦
    0.09
     velocities
    0.09
    è»
    0.08
    Velocity
    0.08
    çĻ¾åĪĨä¹ĭ
    0.08
     зама
    0.08
     velocity
    0.08
    éĢŁ
    0.08
    Activations Density 0.001%

    No Known Activations