© 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. 38494
    Prev
    Next
    INDEX
    Explanations

    positive

    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
    acer
    -0.07
    åľ¨æŁIJäºĽ
    -0.07
    ФС
    -0.07
     Ñįлем
    -0.07
    æľīçĤ¹åĥı
    -0.07
    ä¸į顺
    -0.07
    é»ĺé»ĺåľ°
    -0.07
    å®ĥ们çļĦ
    -0.06
    微信æī«ä¸Ģæī«
    -0.06
    ÑģÑİ
    -0.06
    POSITIVE LOGITS
    æĥŁä¸Ģ
    0.08
    åıªæľīä¸Ģ个
    0.08
    éĺĻ
    0.08
    udid
    0.07
    idium
    0.07
    åıªå¾Ĺ
    0.07
    trin
    0.07
    arif
    0.07
    æ¡ĥ
    0.07
    ministr
    0.07
    Activations Density 0.007%

    No Known Activations