© 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. 18881
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    âĢ¦âĢ¦ãĢĤ
    -0.09
    Âł
    -0.08
    并éĩĩåıĸ
    -0.07
     Âł
    -0.07
     Zir
    -0.07
    ]?.
    -0.07
    âĢ¦ãĢĤ
    -0.07
    ="__
    -0.07
     (`
    -0.06
    ([{
    -0.06
    POSITIVE LOGITS
     uncomment
    0.09
    åĪ°è¿ĻéĩĮ
    0.09
    åľ¨éĢĻ裡
    0.08
     ÙĩÙĨا
    0.08
    è¿ĻéĩĮæĺ¯
    0.08
    åľ¨è¿ĻéĩĮ
    0.08
     here
    0.08
    æѤå¤Ħ
    0.07
    æĿ¥åĪ°è¿ĻéĩĮ
    0.07
     aqui
    0.07
    Activations Density 0.577%

    No Known Activations