© 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. 15264
    Prev
    Next
    INDEX
    Explanations

    numbers, medical terms, place names

    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
    fk
    -0.07
     cms
    -0.07
     Dol
    -0.07
    大çĪ±
    -0.06
    åľ¨é¦Ļ港
    -0.06
    rones
    -0.06
    ÄĻg
    -0.06
    affles
    -0.06
    aleb
    -0.06
    åĬŀ主任
    -0.06
    POSITIVE LOGITS
    Õ¸ÖĢ
    0.07
    trib
    0.07
    _gettime
    0.07
     poil
    0.07
    ttl
    0.07
     ÙĪØ«
    0.07
    容
    0.07
    terra
    0.07
    eye
    0.07
    izas
    0.07
    Activations Density 0.056%

    No Known Activations