© 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. 10239
    Prev
    Next
    INDEX
    Explanations

    exact or precise

    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
    vist
    -0.07
    bel
    -0.06
    iffe
    -0.06
     indiscrim
    -0.06
    OMO
    -0.06
    çħĮ
    -0.06
    ifel
    -0.06
     superficial
    -0.06
    å³¥åµĺ
    -0.06
    ׼×ķ׾
    -0.06
    POSITIVE LOGITS
     exact
    0.13
    Exact
    0.13
    exact
    0.12
    精确
    0.12
     Exact
    0.12
    _exact
    0.11
    rouw
    0.10
    åĩĨç¡®çļĦ
    0.09
    æºĸ確
    0.09
     precise
    0.09
    Activations Density 0.002%

    No Known Activations