© 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. 13290
    Prev
    Next
    INDEX
    Explanations

    alternative characters

    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
    μάÏĦÏīν
    -0.07
    ÙħÙĬØ©
    -0.06
    erti
    -0.06
     sekalipun
    -0.06
    åİĨåİĨ
    -0.06
    icke
    -0.06
    ä½Ĩåıªè¦ģ
    -0.06
    èĢĮä½ľä¸º
    -0.06
    Ù°
    -0.06
    ativos
    -0.06
    POSITIVE LOGITS
    ãģ¨ãģĦãģ£ãģ¦ãĤĤ
    0.11
    ãģ¨è¨Ģãģ£ãģ¦ãĤĤ
    0.10
     appunto
    0.08
    çĻ¾å·Ŀ
    0.08
    æľ¬èº«
    0.07
     inilah
    0.07
    ä¸Ģè¯į
    0.07
    çĻ¾éĩĮ
    0.07
    è¿Ļç§įä¸ľè¥¿
    0.07
    è¿Ļ个è¯į
    0.07
    Activations Density 0.669%

    No Known Activations