© 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. 18173
    Prev
    Next
    INDEX
    Explanations

    number limit

    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
    amai
    -0.06
    uable
    -0.06
    lain
    -0.05
     “
    -0.05
    æĪĸå°ij
    -0.05
    ('^
    -0.05
    elv
    -0.05
    ne
    -0.05
    unte
    -0.05
    agnost
    -0.05
    POSITIVE LOGITS
    spath
    0.06
    ×ļ
    0.06
     ado
    0.06
    æĺ¥åħī
    0.05
    éģŃåĪ°äºĨ
    0.05
    agara
    0.05
    oration
    0.05
     quizá
    0.05
    اÙĨس
    0.05
    اÛĮØ´
    0.05
    Activations Density 0.012%

    No Known Activations