© 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. 38564
    Prev
    Next
    INDEX
    Explanations

    numbers and add/finally

    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
    chter
    -0.08
    åħĭåĬĽ
    -0.07
    _blocked
    -0.07
    å·¥ä½ľçļĦåIJĮæŶ
    -0.07
    irse
    -0.07
    ãģįãĤĭ
    -0.07
    çļĦå¿ĥ声
    -0.07
    erio
    -0.07
    είÏĤ
    -0.06
    replacement
    -0.06
    POSITIVE LOGITS
    åĨįåĬłä¸Ĭ
    0.10
    åĨį
    0.09
    åĬłåħ¥
    0.08
    æľĢåIJİ
    0.08
     finally
    0.07
    åĨį以
    0.07
     acrescent
    0.07
    =add
    0.07
     add
    0.07
    åĨįåĬł
    0.07
    Activations Density 0.001%

    No Known Activations