© 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. 17996
    Prev
    Next
    INDEX
    Explanations

    expansion or 'more'

    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
    aleb
    -0.06
    æŧçļĦ
    -0.06
    ä¸Ń人
    -0.06
     berk
    -0.06
    stoi
    -0.06
     competitivo
    -0.06
    evi
    -0.06
    -org
    -0.06
    wali
    -0.06
     ÙĩÙħÛĮÙĨ
    -0.06
    POSITIVE LOGITS
     expansion
    0.06
     expand
    0.06
    åĬłæĭī
    0.05
     expands
    0.05
    èĨ¨èĥĢ
    0.05
    å±ķå¼Ģ
    0.05
    /l
    0.05
     Expansion
    0.05
     det
    0.05
     expanding
    0.05
    Activations Density 0.048%

    No Known Activations