© 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. 21035
    Prev
    Next
    INDEX
    Explanations

    espresso related phrases

    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
     Pick
    -0.06
     pick
    -0.05
    mouth
    -0.05
    æ¼Ĥæµģ
    -0.05
    åıijå¸ĥåħ¬åijĬ称
    -0.05
     Pot
    -0.05
    bird
    -0.05
    kuti
    -0.05
     perd
    -0.05
    birds
    -0.05
    POSITIVE LOGITS
     Palma
    0.07
    è¯ģ书
    0.06
    emand
    0.06
    iman
    0.06
    avent
    0.06
     personally
    0.06
    åī°
    0.06
    rof
    0.05
    ä¿¡æģ¯ä»ħä¾ĽåıĤèĢĥ
    0.05
     ÙħÙĨا
    0.05
    Activations Density 0.004%

    No Known Activations