© 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. 58439
    Prev
    Next
    INDEX
    Explanations

    that followed by a verb

    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
    wers
    -0.08
    {}\
    -0.07
    »
    -0.07
    <decltype
    -0.07
    IGH
    -0.07
    å¦ĤæѤçļĦ
    -0.06
    spro
    -0.06
    Spo
    -0.06
    ëģĦ
    -0.06
    ipa
    -0.06
    POSITIVE LOGITS
    ç«ĻåĨħæIJľç´¢
    0.08
     uÄŁ
    0.08
    olica
    0.07
    iby
    0.07
    åŃ©åŃIJæĺ¯
    0.07
    åĪ°åĵª
    0.07
     META
    0.07
    å°Ĩæľī
    0.07
    azor
    0.07
    å·²ç»ıå°Ĩ
    0.07
    Activations Density 0.105%

    No Known Activations