© 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. 20923
    Prev
    Next
    INDEX
    Explanations

    nestled, situated, built followed by location 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
     initially
    -0.06
     patern
    -0.06
    Ñĸй
    -0.05
    اØŃ
    -0.05
    vän
    -0.05
    ienza
    -0.05
    áīµ
    -0.05
    ÈĽi
    -0.05
     plank
    -0.05
    iov
    -0.05
    POSITIVE LOGITS
    è¡Ŀ
    0.06
    è¿ĺåºĶ该
    0.06
    群çļĦ
    0.06
    ribly
    0.06
    顯
    0.06
    mus
    0.06
    åį°
    0.05
    resentation
    0.05
    olly
    0.05
    ä¸İä¸ĸçķĮ
    0.05
    Activations Density 0.032%

    No Known Activations