© 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. 47617
    Prev
    Next
    INDEX
    Explanations

    initially or first followed by a description

    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
    ISOString
    -0.08
    acob
    -0.07
    asters
    -0.07
    åı¯éĢīä¸Ń
    -0.07
    å¤įåĪ¶æĪĸ
    -0.07
    erto
    -0.07
    äum
    -0.07
    istir
    -0.07
    Decorator
    -0.07
    dee
    -0.07
    POSITIVE LOGITS
     eerst
    0.09
    åħĪæĺ¯
    0.08
    structured
    0.08
     firstly
    0.08
    ãģ«åĪĨ
    0.08
     hier
    0.08
    åĪĨ为
    0.08
     structure
    0.08
    é¦ĸåħĪæĺ¯
    0.08
    æĿ¡çIJĨ
    0.07
    Activations Density 0.004%

    No Known Activations