© 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. 41154
    Prev
    Next
    INDEX
    Explanations

    if judged that

    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
    оÑĢод
    -0.08
     TUY
    -0.08
    æĴ¥
    -0.07
    ëĶĶìķĦ
    -0.07
    -cli
    -0.07
    æĢİä¹ĪçĶ¨
    -0.07
    è§Ĩé¢ijä¼ļè®®
    -0.07
    åħį费订éĺħ
    -0.07
    -google
    -0.07
    ç¿Ł
    -0.07
    POSITIVE LOGITS
    åĨ³å®ļæĺ¯åIJ¦
    0.10
    æĺ¯åIJ¦
    0.10
     whether
    0.09
    æĺ¯åIJ¦åľ¨
    0.09
     next
    0.09
    ä¸ĭä¸ĢæŃ¥
    0.09
    æĺ¯åIJ¦éľĢè¦ģ
    0.09
     Whether
    0.09
    åĪ¤æĸŃ
    0.08
    æĺ¯åIJ¦åŃĺåľ¨
    0.08
    Activations Density 0.016%

    No Known Activations