© 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. 17580
    Prev
    Next
    INDEX
    Explanations

    experiment number labels

    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
    人
    -0.07
    çĽĬ
    -0.07
    ÙĬÙĨÙĩ
    -0.07
    以åıĬåIJĦç§į
    -0.07
    onces
    -0.06
     Padang
    -0.06
    ustr
    -0.06
    esson
    -0.06
    igans
    -0.06
    çĶ¨
    -0.06
    POSITIVE LOGITS
    ÏĦÏħ
    0.08
    士æŀĹ
    0.07
    quette
    0.07
    scribe
    0.07
    çŃł
    0.07
    ģ
    0.07
    acco
    0.07
    jemu
    0.07
    çļĦäºĭåĬ¡
    0.07
     Kemen
    0.07
    Activations Density 0.003%

    No Known Activations