© 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. 19505
    Prev
    Next
    INDEX
    Explanations

    placeholders and flags

    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
    ÑĢиа
    -0.08
    ppard
    -0.07
    åħ»
    -0.07
    evi
    -0.07
    å±Ģ
    -0.07
     Murdoch
    -0.07
     едино
    -0.07
    ÃŃz
    -0.07
    åĭĺ
    -0.07
    è¯ģ
    -0.07
    POSITIVE LOGITS
    å¸Ĩ
    0.07
    amol
    0.07
    çľ¼éĩĮ
    0.06
     Gav
    0.06
    äºĨæķ´ä¸ª
    0.06
    пÑĢав
    0.06
    Links
    0.06
    ãģ£ãģ¨
    0.06
    è¿ŀæݥ线
    0.06
     اÙĦرب
    0.06
    Activations Density 0.009%

    No Known Activations