© 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. 60294
    Prev
    Next
    INDEX
    Explanations

    gyroscopespinstateseffectvelocitiesswirling

    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
    è£ħ车
    -0.08
    åĬłåĢį
    -0.08
    è¸ıéĿĴ
    -0.08
    åī¯æľ¬
    -0.08
    åĢįå¢ŀ
    -0.07
    اش
    -0.07
    æİĸ
    -0.07
    oura
    -0.07
    Scaler
    -0.07
    åŁºæķ°
    -0.07
    POSITIVE LOGITS
     velocities
    0.07
    _tick
    0.07
     spinning
    0.07
     Giro
    0.07
     vortex
    0.07
    vecs
    0.07
    ç´IJ
    0.07
     velocity
    0.07
     swirling
    0.07
    বà§ĩ
    0.07
    Activations Density 0.002%

    No Known Activations