© 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. 18123
    Prev
    Next
    INDEX
    Explanations

    class definitions, functions, methods

    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
    iliar
    -0.06
    ÙĪØ·
    -0.06
    ibo
    -0.06
    oust
    -0.06
    ubber
    -0.06
    平常
    -0.06
    ugn
    -0.06
    anian
    -0.06
    native
    -0.06
    fila
    -0.06
    POSITIVE LOGITS
    å¸Ń
    0.06
    impin
    0.05
    anya
    0.05
     raff
    0.05
     apl
    0.05
    西西
    0.05
     er
    0.05
     fam
    0.05
     cop
    0.05
    إ
    0.05
    Activations Density 0.058%

    No Known Activations