© 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. 26799
    Prev
    Next
    INDEX
    Explanations

    sequentially connect wires

    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
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    -0.09
    Convertible
    -0.08
    ahas
    -0.08
    转è¿ĩ
    -0.08
    Against
    -0.08
    Stamped
    -0.08
    води
    -0.08
    illac
    -0.08
    代çIJĨæľįåĬ¡
    -0.08
    اشت
    -0.08
    POSITIVE LOGITS
    ä¸į顺
    0.07
    æľīçĤ¹åĥı
    0.07
    æĮĩå®ļçļĦ
    0.07
    è§ĦåĪĻ
    0.07
    ä¸ĢæŦ
    0.06
    zung
    0.06
    (
    0.06
    iner
    0.06
    åĽºå®ļ
    0.06
    éģµå¾ª
    0.06
    Activations Density 0.028%

    No Known Activations