© 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. 19159
    Prev
    Next
    INDEX
    Explanations

    invest in

    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
    è¡Ļ
    -0.07
    ÃŃch
    -0.07
    $o
    -0.07
    érico
    -0.06
    auté
    -0.06
    atto
    -0.06
    .TryParse
    -0.06
    ä¸Ģåĵģ
    -0.06
    ceo
    -0.06
    iru
    -0.06
    POSITIVE LOGITS
    {
    0.05
    ton
    0.05
    uming
    0.05
    anded
    0.05
    ilingual
    0.05
    å¾Ĺèµ·
    0.05
    aged
    0.05
    ated
    0.05
     sob
    0.05
    è´¨çļĦ
    0.05
    Activations Density 0.005%

    No Known Activations