© 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. 60555
    Prev
    Next
    INDEX
    Explanations

    Seebeck effect, Fitts' law, Bragg wavelength

    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
    sas
    -0.07
    们
    -0.07
    AtPath
    -0.07
    åĩ«
    -0.07
    roulette
    -0.07
    estina
    -0.07
    ross
    -0.07
    funcs
    -0.07
    ä¸ĵ家认为
    -0.07
    processable
    -0.07
    POSITIVE LOGITS
    Modal
    0.07
    éķ¿å¤§
    0.07
     law
    0.07
    äºİäºĭ
    0.07
    ä¸İ大
    0.07
    rière
    0.07
    æľīæķĪ
    0.07
     Modal
    0.06
    modal
    0.06
    arkin
    0.06
    Activations Density 0.004%

    No Known Activations