© 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. 12478
    Prev
    Next
    INDEX
    Explanations

    specifically designed

    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
    ÑģÑĤвиÑı
    -0.07
    ä¸įåħ¬å¹³
    -0.07
    空åīį
    -0.07
     presentations
    -0.07
    å¾Ĺ罪
    -0.07
    为人
    -0.07
    _MAY
    -0.07
     Présent
    -0.07
    å°±æĺ¯è¿Ļä¹Ī
    -0.07
    å¿ĥäºĨ
    -0.07
    POSITIVE LOGITS
     preferably
    0.16
    æľĢ好æĺ¯
    0.14
    prefer
    0.12
     möglichst
    0.12
     ideally
    0.11
    èĩ³å°ij
    0.11
     желаÑĤелÑĮно
    0.10
    å°ijãģªãģıãģ¨ãĤĤ
    0.10
     almeno
    0.10
    æľĢ好
    0.10
    Activations Density 0.173%

    No Known Activations