© 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. 56485
    Prev
    Next
    INDEX
    Explanations

    collision, pressure, impact

    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
     Anch
    -0.08
     nắng
    -0.07
    çľºæľĽ
    -0.07
    éħ¸æĢ§
    -0.07
    renal
    -0.07
    Disposition
    -0.07
    碱æĢ§
    -0.07
    неж
    -0.07
     portion
    -0.07
    기ìŀIJ
    -0.07
    POSITIVE LOGITS
     collisions
    0.12
     collision
    0.11
    ollision
    0.10
     Collision
    0.10
    碰æĴŀ
    0.09
    æij©æĵ¦
    0.09
     gas
    0.09
     friction
    0.08
    Collision
    0.08
     충ëıĮ
    0.08
    Activations Density 0.005%

    No Known Activations