© 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. 56251
    Prev
    Next
    INDEX
    Explanations

    also followed by conjunctions or verbs

    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
    ä¹Łå°±æĺ¯
    -0.08
    ä¹Łå°±
    -0.08
     also
    -0.07
    åıĪ称为
    -0.07
    åıĪ以
    -0.07
     maybe
    -0.07
    olini
    -0.06
    ä¸įä»ħ
    -0.06
     Also
    -0.06
    æĪĸä¸į
    -0.06
    POSITIVE LOGITS
    à¹Ģà¸Ĭà¹Īà¸Ļà¸ģัà¸Ļ
    0.13
    eens
    0.11
     ë§Īì°¬ê°Ģì§Ģ
    0.11
     ebenfalls
    0.10
    ä¸į容忽è§Ĩ
    0.09
    ä¸įåı¯å¿½è§Ĩ
    0.09
     ë§Īì°¬
    0.09
    åIJĮæ§ĺ
    0.08
     ë§Īì°¬ê°Ģì§Ģë¡ľ
    0.08
     igualmente
    0.08
    Activations Density 0.107%

    No Known Activations