© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19439
    Prev
    Next
    INDEX
    Explanations

    punctuation and structural elements

    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
    umbo
    -0.08
    autant
    -0.07
    orf
    -0.06
     Sollte
    -0.06
    iril
    -0.06
    ikers
    -0.06
    iston
    -0.06
     Sollten
    -0.06
    bote
    -0.06
    аÑĢа
    -0.06
    POSITIVE LOGITS
    æľ¬èº«
    0.06
    æľ¬æĿ¥
    0.05
    myp
    0.05
     pan
    0.05
    åıĤ
    0.05
    è¶Ł
    0.05
    æĿŀ
    0.05
     conf
    0.05
    ename
    0.05
    ene
    0.05
    Activations Density 0.031%

    No Known Activations