© 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. 26672
    Prev
    Next
    INDEX
    Explanations

    default, machine, human, standard, natural, western

    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
    ambul
    -0.06
    åĴĮéĺ¿
    -0.06
    æıīäºĨæıī
    -0.06
    abouts
    -0.06
    üp
    -0.06
    ST
    -0.06
    åŃ°
    -0.05
     garde
    -0.05
    _misc
    -0.05
    æŁĶæĥħ
    -0.05
    POSITIVE LOGITS
    åİŁæĿ¥çļĦ
    0.11
    åİŁæľī
    0.10
     기존
    0.09
    åİŁæľīçļĦ
    0.09
    åĪ¹
    0.08
    åĩºèį·
    0.08
     기존ìĿĺ
    0.08
    ingo
    0.08
    çİ°æľīçļĦ
    0.08
    æIJ¬
    0.08
    Activations Density 0.151%

    No Known Activations