© 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. 21662
    Prev
    Next
    INDEX
    Explanations

    hub of

    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
    اتÛĮ
    -0.07
    -0.06
    اء
    -0.06
    но
    -0.06
    段çļĦ
    -0.06
    au
    -0.06
    ities
    -0.06
    ural
    -0.06
    ual
    -0.06
    ven
    -0.06
    POSITIVE LOGITS
     amassed
    0.07
    ommy
    0.07
    رÙĩ
    0.07
    plex
    0.07
     verzam
    0.07
    ötz
    0.07
    omot
    0.06
    ÙħÙĥاÙĨ
    0.06
    asper
    0.06
    оÑģÑĤÑĢе
    0.06
    Activations Density 0.003%

    No Known Activations