© 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. 48859
    Prev
    Next
    INDEX
    Explanations

    clostridium or toxin derivatives

    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
    zez
    -0.07
    setQuery
    -0.07
    ä¸įæĮ¯
    -0.07
    ازÙĩ
    -0.07
    á»ı
    -0.07
    èŀįèŀį
    -0.07
    ZA
    -0.07
    wana
    -0.07
    assi
    -0.06
    keit
    -0.06
    POSITIVE LOGITS
    麻çĹ¹
    0.08
     toxin
    0.07
     neuro
    0.07
    icho
    0.07
    รà¹īาย
    0.07
    idis
    0.07
    åį±å®³
    0.07
    pose
    0.07
    ç¥ŀç»ıç³»ç»Ł
    0.07
    éļı身æIJºå¸¦
    0.07
    Activations Density 0.061%

    No Known Activations