© 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. 47884
    Prev
    Next
    INDEX
    Explanations

    return or send

    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¦ģè®¤çľŁ
    -0.07
    è¦ģ好好
    -0.07
    æĿ¥èĩªäºİ
    -0.07
    éľĢè¦ģåIJĮ
    -0.07
    juÄį
    -0.06
    ķ
    -0.06
    uos
    -0.06
    ville
    -0.06
    icont
    -0.06
    ä¹ĭå¤Ħåľ¨äºİ
    -0.06
    POSITIVE LOGITS
    类似
    0.08
    ä¸Ģ个æĸ°
    0.08
    符åIJĪ
    0.07
    æ²ĥæĸ¯
    0.07
    ä¸Ģ个女人
    0.07
     вида
    0.07
    isku
    0.07
    ÅĤas
    0.07
    ut
    0.07
    欲
    0.07
    Activations Density 0.009%

    No Known Activations