© 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. 65217
    Prev
    Next
    INDEX
    Explanations

    regulated by

    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
    Ñĩа
    -0.07
    ë¦ĩ
    -0.07
    zol
    -0.07
     DISCLAIMER
    -0.07
    urr
    -0.07
    ä¸įä¹ħçļĦ
    -0.06
     ضÙħ
    -0.06
    åħĭéĩĮ
    -0.06
    ×¢×Ļ
    -0.06
    obbies
    -0.06
    POSITIVE LOGITS
    å¦Ĥåħ¶
    0.12
     its
    0.12
    åľ¨åħ¶
    0.12
    å®ĥéĤ£
    0.11
    åıĬåħ¶
    0.11
     Its
    0.11
    对åħ¶
    0.10
    以åħ¶
    0.10
    ä»İåħ¶
    0.10
    æĪĸåħ¶
    0.10
    Activations Density 0.875%

    No Known Activations