© 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. 33632
    Prev
    Next
    INDEX
    Explanations

    special relativity, Einstein, quantum mechanical

    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
     kontinu
    -0.08
    ç¼Ń
    -0.08
     izle
    -0.08
    -done
    -0.08
    gypt
    -0.08
    .isOn
    -0.08
    æľĢä½İçļĦ
    -0.08
    itek
    -0.08
    Histogram
    -0.08
    acÃŃ
    -0.08
    POSITIVE LOGITS
    åħīéĢŁ
    0.07
    è¿IJç®Ĺ
    0.07
     relativ
    0.07
     reconc
    0.07
    è¿IJåĬ¨çļĦ
    0.07
    人人éĥ½
    0.07
    åıĸ代
    0.06
     radically
    0.06
    å¤Ħå¤Ħ
    0.06
    åįıè°ĥåıijå±ķ
    0.06
    Activations Density 0.002%

    No Known Activations