© 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. 46083
    Prev
    Next
    INDEX
    Explanations

    cost of inclusion

    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
    idu
    -0.07
    åĽłä¸ºåıªæľī
    -0.07
    åĻ¨
    -0.07
    ewan
    -0.06
    utri
    -0.06
    fil
    -0.06
    bac
    -0.06
    ustes
    -0.06
    orado
    -0.06
    ches
    -0.06
    POSITIVE LOGITS
    åħ¨åĮħ
    0.10
    -package
    0.10
    ä¸įåĮħæĭ¬
    0.09
    bund
    0.09
    åĮħæĭ¬äºĨ
    0.09
     delivery
    0.08
    交ä»ĺ
    0.08
    ä¸įåĮħåIJ«
    0.08
     package
    0.08
     INCLUDED
    0.08
    Activations Density 0.057%

    No Known Activations