© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22221
    Prev
    Next
    INDEX
    Explanations

    sequences like `\d` and `x`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĿĢèĻ«
    -0.06
    ocl
    -0.06
    uger
    -0.05
     uj
    -0.05
    allet
    -0.05
    ylon
    -0.05
     اÙĦبÙĦا
    -0.05
    klan
    -0.05
    渺
    -0.05
    urch
    -0.05
    POSITIVE LOGITS
    de
    0.06
    æĪĪ
    0.06
    æ´¾
    0.06
    uner
    0.06
    imest
    0.06
    å¸Ĥåľºç«ŀäºī
    0.05
    g
    0.05
    ä¹ĭå¤ļ
    0.05
    IEWS
    0.05
    ÙĪÙĤ
    0.05
    Activations Density 0.006%

    No Known Activations