© 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. 12332
    Prev
    Next
    INDEX
    Explanations

    pmod{ }

    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
    ral
    -0.10
    anı
    -0.09
    ième
    -0.09
     tslint
    -0.08
    иж
    -0.08
    াà¦ģ
    -0.08
    ONSE
    -0.08
    à¸Ļà¸Ļ
    -0.08
    ariado
    -0.08
    份åŃIJ
    -0.08
    POSITIVE LOGITS
    çļĦ
    0.06
    0.06
    ä¹İ
    0.06
    åĪ°åºķ
    0.06
    -ish
    0.06
     with
    0.06
    unan
    0.05
    人身
    0.05
    Âł
    0.05
    ../../../
    0.05
    Activations Density 0.001%

    No Known Activations