© 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. 22658
    Prev
    Next
    INDEX
    Explanations

    statistical mechanics and velocity distributions

    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
    延
    -0.07
     nov
    -0.06
     intele
    -0.06
    à¹īำ
    -0.06
     inject
    -0.06
    etime
    -0.06
    æ¸ħæ°´
    -0.06
    ommage
    -0.06
    ä¿ĿæĬ¤å¥½
    -0.06
     incur
    -0.06
    POSITIVE LOGITS
    çļĦæ°Ķä½ĵ
    0.09
     individuais
    0.09
     velocities
    0.09
    æ°Ķä½ĵ
    0.08
    æ°Ķä½ĵçļĦ
    0.08
     velocity
    0.08
     individual
    0.08
    Individual
    0.08
    ividual
    0.08
     gases
    0.08
    Activations Density 0.001%

    No Known Activations