© 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. 22001
    Prev
    Next
    INDEX
    Explanations

    do good

    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
    êµīìŀ¥
    -0.08
    mayan
    -0.08
    꽤
    -0.07
    ostro
    -0.07
    è¢«ä¾ĽåºĶåķĨ
    -0.07
     ÙħÙĤاÙħ
    -0.07
    olim
    -0.07
    azzino
    -0.07
    ÑĢаво
    -0.07
     nÃłn
    -0.07
    POSITIVE LOGITS
    ed
    0.06
    ,
    0.05
    Âł
    0.05
     +
    0.05
    .
    0.05
    illa
    0.05
     circ
    0.05
    æĽľ
    0.05
     m
    0.05
    u
    0.05
    Activations Density 0.012%

    No Known Activations