© 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. 42661
    Prev
    Next
    INDEX
    Explanations

    direction and endpoint

    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
    æĪĸå¤ļ个
    -0.07
    å¤ļæľĪ
    -0.07
    engesch
    -0.07
    ä»İåīį
    -0.07
    /channel
    -0.07
    以ä¸Ĭæĺ¯
    -0.07
    heiten
    -0.07
    Ñİ
    -0.07
    èĥĮåIJİ
    -0.07
    aison
    -0.07
    POSITIVE LOGITS
    most
    0.12
    -most
    0.10
     portion
    0.08
    MOST
    0.08
    -side
    0.07
    side
    0.07
     sekali
    0.07
    สุà¸Ķ
    0.07
    å¿
    0.07
     edge
    0.07
    Activations Density 0.049%

    No Known Activations