© 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. 21151
    Prev
    Next
    INDEX
    Explanations

    configuration directives

    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
    æģ
    -0.07
    SEG
    -0.06
    ä¸įå¼Ģ
    -0.06
    arkin
    -0.06
    iliar
    -0.06
    inters
    -0.06
    ronym
    -0.06
    kana
    -0.06
    /of
    -0.06
    Å¡t
    -0.06
    POSITIVE LOGITS
     mere
    0.06
     Fad
    0.05
    ç«Ļ
    0.05
    Me
    0.05
     ejer
    0.05
    coli
    0.05
    è¢«ä½ł
    0.05
    ä¸įåı¯æĪĸ缺
    0.05
    èIJ½åĪ°å®ŀå¤Ħ
    0.05
    ix
    0.05
    Activations Density 0.011%

    No Known Activations