© 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. 20473
    Prev
    Next
    INDEX
    Explanations

    take off

    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
    rus
    -0.07
    enca
    -0.07
    din
    -0.06
    bart
    -0.06
    и
    -0.06
    heur
    -0.06
    vez
    -0.06
    н
    -0.06
    er
    -0.05
    found
    -0.05
    POSITIVE LOGITS
    ensively
    0.07
    imdi
    0.06
    alom
    0.06
    ÙĪاج
    0.05
    пÑĭ
    0.05
     contrário
    0.05
    å¦ĩ产
    0.05
    .multi
    0.05
    ì¶ľ
    0.05
     squarely
    0.05
    Activations Density 0.001%

    No Known Activations