© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7289
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    resp
    -0.07
    èĵ¬
    -0.06
     Nath
    -0.06
    èĢĥäºĨ
    -0.06
    æľĪä¸Ń
    -0.06
    è¿Ļä¸ĢéĹ®é¢ĺ
    -0.06
    ohen
    -0.06
    .sequence
    -0.05
    å¤ļå°ij
    -0.05
     +
    -0.05
    POSITIVE LOGITS
    åłª
    0.09
    arsed
    0.09
    éħĿ
    0.08
    ymp
    0.08
    ulous
    0.08
    çĶ«
    0.08
    çļĦå¿ĥ声
    0.08
     outFile
    0.08
    Scrollbar
    0.08
    .opensource
    0.07
    Activations Density 0.000%

    No Known Activations