© 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. 21109
    Prev
    Next
    INDEX
    Explanations

    SMART Program

    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
    ickl
    -0.07
    andon
    -0.07
    eci
    -0.07
    åıĬéĻĦåĬł
    -0.07
    erot
    -0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.07
    quee
    -0.07
    igue
    -0.06
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    -0.06
    é±
    -0.06
    POSITIVE LOGITS
    æīĢ以说
    0.08
    æij¸
    0.06
    azz
    0.06
    åħ§å¤ĸ
    0.06
    æĺŁæ²³
    0.06
    ä»Ĭ天å°ıç¼ĸ
    0.06
    ä¹ĸ
    0.06
    áĥĶáĥij
    0.06
    æĻļéĹ´
    0.06
    说è¦ģ
    0.06
    Activations Density 0.009%

    No Known Activations