© 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. 23841
    Prev
    Next
    INDEX
    Explanations

    omic analysis

    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
    iform
    -0.07
    èĩªåĬĽ
    -0.07
    ovable
    -0.07
    (Form
    -0.07
    [table
    -0.07
    aight
    -0.07
    rito
    -0.07
    ajan
    -0.07
    vvm
    -0.06
    该类
    -0.06
    POSITIVE LOGITS
     Thousands
    0.09
    iha
    0.08
     Changes
    0.08
     changes
    0.08
    analysis
    0.08
     signatures
    0.08
    changes
    0.08
     analysis
    0.08
     curated
    0.08
    Whole
    0.07
    Activations Density 0.344%

    No Known Activations