© 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. 20856
    Prev
    Next
    INDEX
    Explanations

    centuries

    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
    Ø«ÙĨÙĬÙĨ
    -0.07
    å¾·æĸ¯
    -0.07
     terc
    -0.07
    ÙĤداÙħ
    -0.07
    UGHT
    -0.07
    ésar
    -0.07
    kraft
    -0.07
    enment
    -0.07
    /Gate
    -0.07
    vice
    -0.06
    POSITIVE LOGITS
    st
    0.06
    ed
    0.05
    l
    0.05
    ·
    0.05
    &
    0.05
    -
    0.05
    al
    0.05
    太
    0.05
    ist
    0.05
    /
    0.05
    Activations Density 0.013%

    No Known Activations