© 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. 21153
    Prev
    Next
    INDEX
    Explanations

    subway or metro station

    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
    oose
    -0.06
    asan
    -0.06
    ulin
    -0.06
     sis
    -0.06
    aged
    -0.06
    pekt
    -0.05
    tep
    -0.05
    ayi
    -0.05
     pe
    -0.05
    ticks
    -0.05
    POSITIVE LOGITS
    бÑı
    0.06
    legg
    0.06
    åľ°ä¸ĭ
    0.06
    niec
    0.06
     underground
    0.06
    ÚĺÛĮ
    0.06
    åľ°ä¸ĭæ°´
    0.05
    ercul
    0.05
    ubre
    0.05
    ç¬ijçļĦ
    0.05
    Activations Density 0.024%

    No Known Activations