© 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. 18393
    Prev
    Next
    INDEX
    Explanations

    example or above

    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
    borough
    -0.06
    æķ´ä½ĵä¸Ĭ
    -0.06
    å¤ļåĽ¾
    -0.06
    yanto
    -0.06
     understandably
    -0.06
    羯
    -0.06
    onsin
    -0.06
    lij
    -0.06
    æĪ¿å®¢
    -0.06
     insgesamt
    -0.06
    POSITIVE LOGITS
    icho
    0.05
    表æĺİ
    0.05
    ante
    0.05
     ëıĮ
    0.05
    apos
    0.05
     Gors
    0.05
    wor
    0.05
     Gol
    0.05
    dam
    0.05
    iation
    0.05
    Activations Density 0.008%

    No Known Activations