© 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. 20953
    Prev
    Next
    INDEX
    Explanations

    attention

    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
    OwnProperty
    -0.11
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.10
    vole
    -0.09
    pch
    -0.08
    indeki
    -0.08
    çİĩåľ¨
    -0.08
    ÑĹв
    -0.08
    iches
    -0.08
    -too
    -0.07
    anke
    -0.07
    POSITIVE LOGITS
    à¤Ĺà¥įर
    0.07
     trot
    0.06
    دار
    0.06
    çĽ¸å¯¹çļĦ
    0.06
    à¹Ģà¸ģิà¸Ķà¸Ĥึà¹īà¸Ļ
    0.06
    æīĢè°ĵçļĦ
    0.06
    åı¯
    0.06
    arre
    0.06
     forthcoming
    0.06
    éĻį临
    0.06
    Activations Density 0.076%

    No Known Activations