© 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. 41327
    Prev
    Next
    INDEX
    Explanations

    stolen, tasting, full, families, instructional, educational, smoke, consumption

    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
    åħ®
    -0.08
    cpy
    -0.08
    ecker
    -0.08
    _AXIS
    -0.08
    erma
    -0.07
    empi
    -0.07
    æĹłå°ĺ
    -0.07
     Rady
    -0.07
    ayu
    -0.07
    WISE
    -0.07
    POSITIVE LOGITS
    çļĦåħ¶ä»ĸ
    0.09
    ä¹±
    0.07
    /GPL
    0.07
    qr
    0.07
    Âł
    0.07
     lainnya
    0.06
    à¸Ńืà¹Īà¸Ļà¹Ĩ
    0.06
     sogar
    0.06
     Âł
    0.06
    åħ¶å®ĥ
    0.06
    Activations Density 0.816%

    No Known Activations