© 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. 20500
    Prev
    Next
    INDEX
    Explanations

    how can i

    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
    åħĪå¾Ĺ
    -0.08
    åľ¨å»º
    -0.07
    æĺ¯ä»Ģä¹Īæł·çļĦ
    -0.07
    uess
    -0.07
    ç¾Ķ
    -0.07
    æĺ¯æĢİä¹Ī
    -0.07
    essential
    -0.07
    éĺħè¯»æľ¬æĸĩåīį
    -0.06
    ugat
    -0.06
    æĺ¯æĢİæł·çļĦ
    -0.06
    POSITIVE LOGITS
     we
    0.08
    estos
    0.07
    nos
    0.07
     you
    0.07
    nous
    0.07
    ring
    0.07
     اÙĦÙħÙħÙĥÙĨ
    0.07
    ver
    0.07
    nga
    0.07
    æľīæѤ
    0.07
    Activations Density 0.046%

    No Known Activations