© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57139
    Prev
    Next
    INDEX
    Explanations

    plate, pipe, engine, disease, muscle, connection

    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
    ả
    -0.07
    ÏĦαι
    -0.06
    çĦ¶åIJİçĶ¨
    -0.06
    æĹłåģ¿çĮ®è¡Ģ
    -0.06
    änn
    -0.06
    ;s
    -0.06
    èĢĮä¸İ
    -0.06
    vironment
    -0.06
    гÑĸ
    -0.06
    agger
    -0.06
    POSITIVE LOGITS
    å¦
    0.07
     коÑĤоÑĢого
    0.07
    enk
    0.07
    åĪ°åºķ
    0.07
     cioè
    0.07
    uchu
    0.07
    两åѦä¸Ģåģļ
    0.07
    éŃĦ
    0.06
    ãģ«éĻIJ
    0.06
    شر
    0.06
    Activations Density 0.413%

    No Known Activations