© 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. 28486
    Prev
    Next
    INDEX
    Explanations

    differential equation components

    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
    ubl
    -0.07
    utsch
    -0.07
    ravi
    -0.07
    odle
    -0.07
    assar
    -0.07
    θεν
    -0.07
    éĺľ
    -0.06
    iach
    -0.06
     rtrim
    -0.06
    пÑĢа
    -0.06
    POSITIVE LOGITS
    çİ¥
    0.07
    äºĶ次
    0.07
     Territory
    0.07
    ToFit
    0.07
    iefe
    0.07
    å¿ĺ
    0.07
    éĸ¢
    0.07
    lk
    0.07
    å¼Ł
    0.07
    èĩªæĪijçļĦ
    0.06
    Activations Density 0.004%

    No Known Activations