© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23326
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code syntax

    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
     subtly
    -0.08
     subtle
    -0.08
    轻微çļĦ
    -0.07
    swick
    -0.07
    轻微
    -0.07
     slight
    -0.07
    ieni
    -0.06
     Growing
    -0.06
     growing
    -0.06
    è¿ĶåĽŀ顶éĥ¨
    -0.06
    POSITIVE LOGITS
    è¶Ĭä½İ
    0.09
    缩
    0.08
    èIJİ缩
    0.08
    èĩªå°Ĭ
    0.08
    annah
    0.08
    alb
    0.07
    å¾Īä½İ
    0.07
    縮
    0.07
    æĭĸç´¯
    0.07
     drastic
    0.07
    Activations Density 0.005%

    No Known Activations