© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18819
    Prev
    Next
    INDEX
    Explanations

    access token

    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
    otre
    -0.06
    usti
    -0.06
    Pretty
    -0.06
    arÄĥ
    -0.06
    ÃŃss
    -0.06
    osexual
    -0.06
     Pretty
    -0.06
    esser
    -0.06
    åIJİæĦŁ
    -0.05
    úst
    -0.05
    POSITIVE LOGITS
    å¥½åľ¨
    0.06
    odate
    0.06
    æłĵ
    0.05
    roj
    0.05
    æĸ¹ä¾¿
    0.05
    å¾·åįİ
    0.05
     sure
    0.05
    æ¯ı个
    0.05
     glad
    0.05
     MAT
    0.05
    Activations Density 0.031%

    No Known Activations