© 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. 10251
    Prev
    Next
    INDEX
    Explanations

    ejection velocities

    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
    大家åºŃ
    -0.06
    æĤ¦
    -0.06
    佳人
    -0.06
    åĶij
    -0.06
    åŃ¦å£«
    -0.06
     indoor
    -0.06
     dese
    -0.06
    ÑĢаÑħ
    -0.06
    вен
    -0.06
    /il
    -0.06
    POSITIVE LOGITS
     velocities
    0.11
    velocity
    0.11
    æµģéĢŁ
    0.10
     velocity
    0.10
    Velocity
    0.10
     ejected
    0.10
     Velocity
    0.10
    _velocity
    0.10
    éĢŁåº¦åĴĮ
    0.09
    éĢŁåº¦
    0.09
    Activations Density 0.017%

    No Known Activations