© 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. 8333
    Prev
    Next
    INDEX
    Explanations

    return new

    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
    inally
    -0.07
    hood
    -0.07
    ron
    -0.07
    éĽ£éģĵ
    -0.07
    otle
    -0.07
    åĪ¹
    -0.07
    ollen
    -0.07
    apper
    -0.07
    çļĦä¸Ģèĩ´å¥½è¯Ħ
    -0.07
    aco
    -0.07
    POSITIVE LOGITS
    ASSES
    0.07
    áĢ®
    0.07
    æŃ¢
    0.07
    stitu
    0.07
    éĩĮ
    0.07
    åĬĽå¼º
    0.07
    ;}
    0.06
    ix
    0.06
    æĪijäºĨ
    0.06
    ynd
    0.06
    Activations Density 0.031%

    No Known Activations