© 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. 17129
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    æīĭ
    -0.06
    æķ´
    -0.06
    èĩ´
    -0.05
    are
    -0.05
     Hand
    -0.05
    âĢ¦
    -0.05
     representing
    -0.05
    -0.05
     pell
    -0.05
     hand
    -0.05
    POSITIVE LOGITS
    andt
    0.07
    onge
    0.07
    oroz
    0.07
    ossi
    0.07
    åĴĮ群ä¼Ĺ
    0.07
    uchtet
    0.07
    å¼Ł
    0.06
    ä¸Ńæĸ°
    0.06
    otel
    0.06
    ä¸Ń游
    0.06
    Activations Density 0.001%

    No Known Activations