© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18588
    Prev
    Next
    INDEX
    Explanations

    conjunctions and foreign words

    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
    argas
    -0.06
    kannya
    -0.06
    å°Ĩä¸Ģ个
    -0.06
    %X
    -0.06
    yorum
    -0.06
    tioner
    -0.06
    argo
    -0.06
    æĸ¹å¼ı为
    -0.06
    à¹ģà¸ŀร
    -0.06
    æĬĬä¸Ģ个
    -0.06
    POSITIVE LOGITS
    Ø©
    0.06
    ation
    0.06
    0.06
    man
    0.06
    ting
    0.06
    al
    0.06
    Âł
    0.05
    äºīåģļ
    0.05
    ÃŁen
    0.05
     the
    0.05
    Activations Density 0.010%

    No Known Activations