© 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. 43807
    Prev
    Next
    INDEX
    Explanations

    last names like Patterson, Spencer

    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
    ÏĦαν
    -0.08
    ourage
    -0.07
    æķĽ
    -0.07
    ingkat
    -0.07
     Byrne
    -0.07
    agnol
    -0.07
    iage
    -0.06
    çļĦèĥĮå½±
    -0.06
    çĻ»å½ķåIJİæŁ¥çľĭ
    -0.06
    微信æī«çłģ
    -0.06
    POSITIVE LOGITS
    ipan
    0.07
    éĢĹ
    0.07
     {*
    0.07
    otron
    0.07
    гов
    0.07
    allen
    0.07
    YW
    0.07
    Compat
    0.07
    зов
    0.06
    Seen
    0.06
    Activations Density 0.613%

    No Known Activations