© 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. 33277
    Prev
    Next
    INDEX
    Explanations

    multiobjective formulation

    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
    ×ķ×IJ
    -0.07
    Ļ
    -0.07
    åħ»æĪIJ
    -0.07
     Wys
    -0.07
    ibar
    -0.07
    åĿIJäºĨ
    -0.06
    çļĦé¢Ĩ导
    -0.06
    æľĽåİ»
    -0.06
    è¦ģé«ĺ度éĩįè§Ĩ
    -0.06
    书éĿ¢
    -0.06
    POSITIVE LOGITS
    ware
    0.08
    æĿ¥èĩªäºİ
    0.07
    à¸Ħืà¸Ńà¸ģาร
    0.07
    å°±æĺ¯æĪij们
    0.07
    à¸Ħืà¸Ń
    0.07
     costituita
    0.07
    .fromString
    0.07
    æĿ¥èĩª
    0.07
    å½ĵçĦ¶æĺ¯
    0.07
    å°±æĺ¯ä½ł
    0.07
    Activations Density 0.144%

    No Known Activations