© 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. 30452
    Prev
    Next
    INDEX
    Explanations

    places and states

    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
    ain
    -0.07
    -President
    -0.07
    ang
    -0.06
    çª
    -0.06
     Productions
    -0.06
    æĸĩ件ä¸Ń
    -0.06
    Å¡
    -0.06
    achel
    -0.06
    è¿ĩå¾Ģ
    -0.06
     Unido
    -0.06
    POSITIVE LOGITS
    'S
    0.10
    ’S
    0.09
    诣
    0.08
    为åģļ好
    0.07
    DataGridViewTextBoxColumn
    0.07
     guarante
    0.07
    RootElement
    0.07
    soever
    0.07
    edith
    0.07
    åı¯æĪij
    0.07
    Activations Density 1.043%

    No Known Activations