© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10804
    Prev
    Next
    INDEX
    Explanations

    word followed by article or noun

    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
     gehe
    -0.08
    dings
    -0.07
    ÎŃ
    -0.07
    acionamento
    -0.07
    åħ·æľīè¾ĥ强çļĦ
    -0.07
    ä¸Ģæ°Ķ
    -0.07
     пеÑĢÑģо
    -0.07
    мка
    -0.07
    ä¸įè¨Ģ
    -0.07
    çĹĩ
    -0.07
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.07
    [#
    0.06
    cheid
    0.06
    ç¥ŀä¹ĭ
    0.06
    å½¢å¼ıçļĦ
    0.06
    á»ijt
    0.06
    å¤ļå¤Ħ
    0.06
     íĺķíĥľìĿĺ
    0.06
     isinstance
    0.06
    Supported
    0.06
    Activations Density 0.137%

    No Known Activations