© 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. 45116
    Prev
    Next
    INDEX
    Explanations

    confidence and confident

    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
    ¶
    -0.09
    ertz
    -0.08
    kinson
    -0.08
    celli
    -0.08
    ugin
    -0.08
    sweise
    -0.07
     mầm
    -0.07
    affer
    -0.07
    ç¢Į
    -0.07
    izable
    -0.07
    POSITIVE LOGITS
    uous
    0.09
    èµ·è§ģ
    0.09
    åįģ足çļĦ
    0.09
    volmente
    0.09
    vole
    0.08
    amment
    0.08
    volle
    0.08
    idence
    0.08
    éĺ³å¸Ĥ
    0.08
    voli
    0.08
    Activations Density 0.010%

    No Known Activations