© 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. 51197
    Prev
    Next
    INDEX
    Explanations

    Sardar, nan, Partnership, karma

    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
    arris
    -0.09
    áĥłáĥĿ
    -0.08
    ocha
    -0.08
    ogie
    -0.07
    å°ī
    -0.07
    ikke
    -0.07
    avel
    -0.07
    ulan
    -0.07
    —not
    -0.07
     viag
    -0.07
    POSITIVE LOGITS
     definition
    0.10
    çļĦå®ļä¹ī
    0.10
    æĺ¯æĮĩ
    0.10
    å®ļä¹ī
    0.09
    æĺ¯æĮĩåľ¨
    0.09
    å®ļä¹ī为
    0.09
    å®ļ義
    0.09
     defined
    0.09
     Definition
    0.09
    æĮĩ
    0.08
    Activations Density 0.456%

    No Known Activations