© 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. 40479
    Prev
    Next
    INDEX
    Explanations

    numbers and statistics

    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
    åĢĴ
    -0.07
    âľ
    -0.06
     FUCK
    -0.06
    dÃŃ
    -0.06
    æįī
    -0.06
     ancestral
    -0.06
     ละ
    -0.06
    atak
    -0.06
    æľĿåįĹ
    -0.06
    bile
    -0.06
    POSITIVE LOGITS
    ana
    0.09
    ItemList
    0.08
    å°±å®ĮæĪIJäºĨ
    0.07
    untime
    0.07
    .osgi
    0.07
     CIT
    0.07
    å¼ķ
    0.07
    _DRAW
    0.07
     dikutip
    0.07
    RootElement
    0.07
    Activations Density 0.003%

    No Known Activations