© 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. 24150
    Prev
    Next
    INDEX
    Explanations

    career, data, types, costs, county, activist, reviews, corruption, football, heterogeneity

    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
     **
    -0.08
     whichever
    -0.07
     */,
    -0.07
     respective
    -0.07
     either
    -0.07
     wÅĤaÅĽnie
    -0.07
     whatever
    -0.07
    .*,
    -0.07
     *
    -0.06
     **.**
    -0.06
    POSITIVE LOGITS
    ÙĢÙĢÙĢÙĢ
    0.08
    ÙĢÙĢÙĢÙĢÙĢÙĢÙĢÙĢ
    0.08
    ADVERTISEMENT
    0.08
    -lnd
    0.07
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.07
    çľ¼è§ģ
    0.07
     versus
    0.07
     vs
    0.07
    stu
    0.07
    ç»ĵè¯Ń
    0.07
    Activations Density 1.390%

    No Known Activations