© 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. 15444
    Prev
    Next
    INDEX
    Explanations

    chiral chemical structures

    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
    :o
    -0.07
    åħ¶å®ĥ
    -0.06
    we
    -0.06
    å¿Ĺ
    -0.06
     rest
    -0.06
    ToJson
    -0.06
    缨
    -0.06
    缮æĮĩ
    -0.06
     other
    -0.06
     autres
    -0.06
    POSITIVE LOGITS
    Å¡em
    0.08
     odre
    0.08
    udahan
    0.08
    warts
    0.08
    adena
    0.08
    ä¸įåı¯æĢĿè®®
    0.08
    geführ
    0.08
    áv
    0.08
    è§Ĥä¼Ĺ们
    0.08
    çĽijå±Ģ
    0.07
    Activations Density 0.075%

    No Known Activations