© 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. 57144
    Prev
    Next
    INDEX
    Explanations

    american revolution

    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
    æ°´ä¸ŃçļĦ
    -0.07
     nearby
    -0.07
    äge
    -0.07
    famil
    -0.06
    æ°´åİĭ
    -0.06
    ULLET
    -0.06
    ä¸į失
    -0.06
    æ³ķåĪĻ
    -0.06
    esar
    -0.06
     Armed
    -0.06
    POSITIVE LOGITS
    ç¥ī
    0.08
    amet
    0.07
    æĺ¯åIJ§
    0.07
    ideo
    0.07
    amar
    0.07
    ihan
    0.07
    éŃ
    0.07
    åIJ¦
    0.07
    umm
    0.07
    èĢĮç«ĭ
    0.07
    Activations Density 0.005%

    No Known Activations