© 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. 47781
    Prev
    Next
    INDEX
    Explanations

    judicial investigation, sanitary safety, decorative arts

    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
     Afgan
    -0.09
    å°Ķé¡¿
    -0.08
     Hanson
    -0.08
     koal
    -0.08
     nonzero
    -0.08
    ÙĬØ«
    -0.08
     partn
    -0.08
     awhile
    -0.08
     corrup
    -0.08
     Nearly
    -0.07
    POSITIVE LOGITS
     (*
    0.08
     expressly
    0.07
     denounced
    0.07
     («
    0.07
     duly
    0.07
     (...)
    0.07
    ogn
    0.07
    itary
    0.07
    imon
    0.07
     pra
    0.07
    Activations Density 0.325%

    No Known Activations