© 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. 28000
    Prev
    Next
    INDEX
    Explanations

    begin definitions

    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
    å¹³å®ī
    -0.07
    ermann
    -0.07
    第äºĮ次
    -0.07
    (PR
    -0.06
    第ä¸ī次
    -0.06
    aal
    -0.06
    éĢļè¿ĩå¼Ģå±ķ
    -0.06
    ahl
    -0.06
    å¹´å¹¼
    -0.06
    pere
    -0.06
    POSITIVE LOGITS
     appunto
    0.08
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    0.08
    èµ·æīĭ
    0.08
    ç¡®æľī
    0.08
     jinak
    0.07
     ä»ĬæĹ¥ãĤĤ
    0.07
    >>()
    0.07
    cito
    0.07
    á»ĩu
    0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.07
    Activations Density 0.007%

    No Known Activations