© 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. 4084
    Prev
    Next
    INDEX
    Explanations

    pros and cons

    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
    让åħ¶
    -0.07
    iness
    -0.07
    æĺ¾å¾Ĺå¾Ī
    -0.07
    inger
    -0.06
    管æīĢ
    -0.06
    èĩĬ
    -0.06
    ied
    -0.06
    ä»İåħ¶
    -0.06
    jan
    -0.06
    çªľ
    -0.06
    POSITIVE LOGITS
    æĸ¹éĿ¢
    0.10
    æĸ¹éĿ¢æľī
    0.08
    ï¼ļ
    0.07
    entities
    0.07
    лама
    0.07
     aspects
    0.07
    bey
    0.07
    æľ¬æĸĩéĵ¾æİ¥
    0.07
    inator
    0.07
    ascal
    0.07
    Activations Density 0.084%

    No Known Activations