© 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. 23976
    Prev
    Next
    INDEX
    Explanations

    faster than light or sound 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
    arsing
    -0.09
     decentral
    -0.08
    缮ä¸į
    -0.08
    endas
    -0.07
    acher
    -0.07
    äch
    -0.07
    .alloc
    -0.07
    åıĹç²¾åįµ
    -0.07
    zeci
    -0.07
     manh
    -0.07
    POSITIVE LOGITS
     speeding
    0.10
     speed
    0.09
     speeds
    0.09
    éĢļ讯
    0.08
    éĢŁåº¦
    0.08
    (speed
    0.08
    é«ĺéĢŁ
    0.08
    à¸Ħวามà¹Ģรà¹ĩว
    0.08
    celer
    0.08
     Speed
    0.08
    Activations Density 0.005%

    No Known Activations