© 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. 21420
    Prev
    Next
    INDEX
    Explanations

    correctly formatted

    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
    erton
    -0.07
    å²Ĥä¸įæĺ¯
    -0.07
    æ¯Ķæĸ¹
    -0.07
    âĢ¦),
    -0.07
    estas
    -0.07
    enes
    -0.07
    ä¸įéļ¾çľĭåĩº
    -0.07
    ught
    -0.07
    ä¸įæķ£
    -0.07
     목ìłģìľ¼ë¡ľ
    -0.07
    POSITIVE LOGITS
    è¿Ļä¸ĢçĤ¹
    0.10
    éĢĻä¸Ģé»ŀ
    0.08
    è¿ĻçĤ¹
    0.08
     nhé
    0.08
    ä¹Łè¦ģ注æĦı
    0.08
    agem
    0.08
    opp
    0.07
    ellent
    0.07
    éĢĻé»ŀ
    0.07
    ķ
    0.07
    Activations Density 0.079%

    No Known Activations