© 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. 23734
    Prev
    Next
    INDEX
    Explanations

    introduces topics or summaries

    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
     truc
    -0.07
    èİ«åIJįçļĦ
    -0.07
    ede
    -0.07
    uggest
    -0.07
     mirac
    -0.07
    vers
    -0.06
     Peker
    -0.06
    icke
    -0.06
    çĶļèĢħ
    -0.06
    å¤ĸéĿ¢
    -0.06
    POSITIVE LOGITS
    dig
    0.07
    åĩĿ
    0.07
     concise
    0.07
    åħ³éĶ®çݯèĬĤ
    0.07
    æĸ
    0.07
    loom
    0.07
    åĪĨç«Ļ
    0.07
    heet
    0.07
    .edu
    0.06
    é»ĦçīĽ
    0.06
    Activations Density 0.016%

    No Known Activations