© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61818
    Prev
    Next
    INDEX
    Explanations

    adenine and cyclic compounds

    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
    ↵
    -0.06
    ↵↵
    -0.06
     tess
    -0.06
    ä¸Ń人
    -0.06
    ä¸įæ²»
    -0.06
    elius
    -0.06
    颤
    -0.05
    éĻ¶
    -0.05
    igg
    -0.05
    å¦Ĥæ°´
    -0.05
    POSITIVE LOGITS
    laatst
    0.09
     prega
    0.08
    èĭ±æĸĩåIJį
    0.08
    ä¾ĽåºĶ产åĵģ
    0.08
    ç½ijç«Ļ导èĪª
    0.08
     somew
    0.08
    utex
    0.08
    æݧèĤ¡éĽĨåĽ¢æľīéĻIJåħ¬åı¸
    0.08
    estring
    0.08
    SocketAddress
    0.08
    Activations Density 0.045%

    No Known Activations