© 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. 30882
    Prev
    Next
    INDEX
    Explanations

    speed and acceleration

    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
    iban
    -0.08
    çĥŃæĴŃ
    -0.08
    ={({
    -0.08
    ìķ¤
    -0.08
    Ŀ
    -0.08
    onnier
    -0.08
    ìłĦìŀ¬
    -0.07
    sker
    -0.07
    .factor
    -0.07
    least
    -0.07
    POSITIVE LOGITS
     gradually
    0.08
    éĢIJæ¸IJ
    0.08
     braking
    0.08
     terminal
    0.07
     mph
    0.07
    æľīä¸Ģ段
    0.07
    terminal
    0.07
     gradual
    0.07
    çŁ¢
    0.07
    arden
    0.06
    Activations Density 0.001%

    No Known Activations