© 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. 49846
    Prev
    Next
    INDEX
    Explanations

    's why

    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
    æĪijæľīä¸Ģ个
    -0.08
    ANH
    -0.08
    ç±³å°Ķ
    -0.07
    ORED
    -0.07
    -prev
    -0.07
     anonim
    -0.07
    çŀ»
    -0.07
     подкоÑĢ
    -0.07
     addirittura
    -0.07
    anoi
    -0.07
    POSITIVE LOGITS
    è°ĵä¹ĭ
    0.09
    è¿Ļå°±æĺ¯
    0.08
     wÅĤaÅĽnie
    0.08
     inilah
    0.08
    æīĢè°ĵçļĦ
    0.07
    被称为
    0.07
     why
    0.07
    ãģ¾ãģķãģ«
    0.07
    åħ¸åŀĭçļĦ
    0.07
    érant
    0.07
    Activations Density 0.065%

    No Known Activations