© 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. 64416
    Prev
    Next
    INDEX
    Explanations

    Toxoplasma gondii

    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
    鲸
    -0.08
    æĬĢå·§
    -0.07
    æĺ¥èĬ±
    -0.07
     Narc
    -0.06
    èĸĦ
    -0.06
    è£ģ
    -0.06
    纯粹
    -0.06
    ä»»
    -0.06
    riger
    -0.06
    éĽªèĬ±
    -0.06
    POSITIVE LOGITS
    ingang
    0.08
    IDL
    0.08
    dio
    0.08
     ingestion
    0.08
    æĥĬéĻ©
    0.08
    éĻ©
    0.08
    zure
    0.08
    马éŀį
    0.08
    via
    0.08
    verte
    0.08
    Activations Density 0.163%

    No Known Activations