© 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. 13976
    Prev
    Next
    INDEX
    Explanations

    variable assignment `=`

    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
    uy
    -0.08
    太è¡Į
    -0.08
    vs
    -0.08
    à¹Ģà¸Ķีย
    -0.07
    çī¹æĸ°
    -0.07
    æ®·
    -0.07
    گرد
    -0.07
    nyi
    -0.07
    VML
    -0.07
    æĽľ
    -0.07
    POSITIVE LOGITS
    çļĦå¿ĥéĩĮ
    0.07
    åıĹ害
    0.07
    æĺ¯æŶåĢĻ
    0.06
    \\/
    0.06
    çŃĿ
    0.06
    .cat
    0.06
    å°±æĺ¯è¿Ļ个
    0.06
    лоÑĤо
    0.06
     cat
    0.06
    æīĢæľīçļĦ
    0.06
    Activations Density 0.002%

    No Known Activations