© 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. 12498
    Prev
    Next
    INDEX
    Explanations

    "explore" followed by punctuation or "If"

    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
    —at
    -0.07
    lier
    -0.07
    Ç
    -0.07
    ysi
    -0.07
    rego
    -0.06
    licity
    -0.06
    cko
    -0.06
    çĩķ
    -0.06
    .addObject
    -0.06
     ↵↵↵
    -0.06
    POSITIVE LOGITS
    æīİå®ŀåģļ好
    0.07
    éģ½
    0.07
    elser
    0.07
    asca
    0.07
    纶
    0.07
    eds
    0.07
    جاÙħ
    0.06
    ìĨĮìŀ¬
    0.06
    _owner
    0.06
    izont
    0.06
    Activations Density 0.001%

    No Known Activations