© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14671
    Prev
    Next
    INDEX
    Explanations

    eukaryotic

    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
    mith
    -0.08
    gage
    -0.08
    हà¥ĩ
    -0.07
    äºĶéĩij
    -0.07
    AndWait
    -0.07
    Äĥng
    -0.07
    âĸ·
    -0.07
    åįĥç§ĭ
    -0.07
    raq
    -0.07
     Inox
    -0.07
    POSITIVE LOGITS
     multic
    0.09
    _cpus
    0.08
    opsis
    0.08
    oslav
    0.08
    endorf
    0.07
     scrambling
    0.07
    endom
    0.07
    eri
    0.07
     cells
    0.07
    enzi
    0.07
    Activations Density 0.013%

    No Known Activations