© 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. 23091
    Prev
    Next
    INDEX
    Explanations

    subtracting from

    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
    éĢı
    -0.08
    驻马
    -0.08
    æĺ¯ç»ı
    -0.08
    aktu
    -0.07
    åĢįå¢ŀ
    -0.07
    ÑĢаÑĤно
    -0.07
    麾
    -0.07
     Bref
    -0.07
    å°Ĭ
    -0.07
    egó
    -0.07
    POSITIVE LOGITS
     subtract
    0.11
    åĩıæ³ķ
    0.09
     Subtract
    0.09
     subtraction
    0.08
    /perl
    0.08
     neutral
    0.08
    ä¸ŃæĢ§
    0.08
    Neutral
    0.08
    (+
    0.08
    neutral
    0.08
    Activations Density 0.012%

    No Known Activations