© 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. 34072
    Prev
    Next
    INDEX
    Explanations

    insolent, regarded as, person, decisive

    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
    enga
    -0.09
    reten
    -0.09
    ñado
    -0.08
    feuer
    -0.08
    åĬĽãģ¯
    -0.08
    engan
    -0.08
    æ²Ļæ²Ļ
    -0.08
    ÑĤÑĩ
    -0.08
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.08
    ç´³
    -0.08
    POSITIVE LOGITS
    æĬĬäºĭæĥħ
    0.06
    ä¸ĢçĤ¹åĦ¿
    0.06
    顺便
    0.06
    äºĭçī©çļĦ
    0.06
     quoted
    0.06
    ä¸Ģä¸ĭåŃIJ
    0.06
    å¼ķçĶ³
    0.06
     Mog
    0.06
     something
    0.06
    çļĦäºĭçī©
    0.06
    Activations Density 0.003%

    No Known Activations