© 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. 58380
    Prev
    Next
    INDEX
    Explanations

    `and` followed by separator or value

    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
     little
    -0.06
    aly
    -0.06
    ä¸ĵçĶ¨
    -0.05
    rer
    -0.05
    ette
    -0.05
    åIJijæĪij们
    -0.05
    little
    -0.05
    лад
    -0.05
    ä¸Ĭ天
    -0.05
    (
    -0.05
    POSITIVE LOGITS
    /or
    0.09
    ÑģÑĤÑİ
    0.08
    éĽģå¡Ķ
    0.08
    ÙĩÙĬ
    0.08
    orent
    0.08
     horor
    0.08
    ×Ļת×Ļ
    0.08
    QUOTE
    0.08
    usercontent
    0.08
    èĭ±æĸĩåIJįåŃĹ
    0.08
    Activations Density 0.139%

    No Known Activations