© 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. 23751
    Prev
    Next
    INDEX
    Explanations

    feeling of certainty

    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
    ogonal
    -0.09
    atiche
    -0.08
    peri
    -0.08
    estad
    -0.08
    -done
    -0.08
    aida
    -0.08
    atico
    -0.07
    yles
    -0.07
    icano
    -0.07
    ä¸Ģé½IJ
    -0.07
    POSITIVE LOGITS
    身åIJİ
    0.07
    hing
    0.07
    DED
    0.06
    æĹ
    0.06
    Ñĸй
    0.06
    åĬĽäºī
    0.06
     React
    0.06
    æĺ
    0.06
    reen
    0.06
    主çļĦ
    0.06
    Activations Density 0.004%

    No Known Activations