© 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. 24873
    Prev
    Next
    INDEX
    Explanations

    exactness and precision

    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
    ilah
    -0.07
    imana
    -0.07
    æĢ»ä¸įèĥ½
    -0.07
    ills
    -0.07
    çIJĨæīĢå½ĵçĦ¶
    -0.07
    enge
    -0.07
     naturally
    -0.07
    æĪĸèĢħ缴æİ¥
    -0.06
    loyd
    -0.06
    itze
    -0.06
    POSITIVE LOGITS
     exact
    0.11
    exact
    0.10
    Exact
    0.10
     wording
    0.10
    精确
    0.09
    åĮħæĭ¬
    0.09
     exactly
    0.09
    _exact
    0.09
     precise
    0.09
     Exact
    0.09
    Activations Density 0.024%

    No Known Activations