© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16290
    Prev
    Next
    INDEX
    Explanations

    printing output

    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
    iliki
    -0.08
    anded
    -0.08
    ×¥
    -0.08
    lement
    -0.08
    akwa
    -0.08
    edException
    -0.08
    urlencode
    -0.08
    佬
    -0.08
    èĢĥçļĦ
    -0.07
    è¦ģç´§
    -0.07
    POSITIVE LOGITS
    念
    0.07
    ä¸įä¸Ģ
    0.07
    inz
    0.07
     "
    0.07
     mát
    0.06
    çļĦéĥ½æĺ¯
    0.06
    人
    0.06
    åħ¶ä¸ŃçļĦ
    0.06
    ÑĨеп
    0.06
    å¾ĹæĽ´
    0.06
    Activations Density 0.069%

    No Known Activations