© 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. 40696
    Prev
    Next
    INDEX
    Explanations

    one at a time

    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
    ogh
    -0.08
    orris
    -0.08
    elier
    -0.07
    ä¸ĢéĢļ
    -0.07
    åħīæĺ¯
    -0.07
    ä¸ĢçĽĨ
    -0.07
    ä¸įæīĵ
    -0.07
    datal
    -0.07
    èIJ¨å°Ķ
    -0.07
    ously
    -0.06
    POSITIVE LOGITS
     individually
    0.12
    åįķ个
    0.12
     incremental
    0.12
    ãģļãģ¤
    0.11
    éĢIJ个
    0.11
    ìĶ©
    0.11
     separately
    0.10
     individual
    0.10
    ä¸Ģ个ä¸Ģ个
    0.10
    ä¸Ģ个个
    0.10
    Activations Density 0.139%

    No Known Activations