© 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. 19605
    Prev
    Next
    INDEX
    Explanations

    many-particle systems

    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
     incub
    -0.08
    endar
    -0.07
    anch
    -0.07
    λει
    -0.07
     flush
    -0.07
    èĬ½
    -0.07
    roma
    -0.07
    她表示
    -0.07
    uring
    -0.06
    nost
    -0.06
    POSITIVE LOGITS
    gaste
    0.08
     collective
    0.08
     histories
    0.08
     coordinate
    0.07
     swarm
    0.07
    èļ
    0.07
     molecule
    0.07
    两å¥Ĺ
    0.07
     bodies
    0.07
     interactions
    0.07
    Activations Density 0.007%

    No Known Activations