© 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. 18518
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    pe
    -0.05
    erty
    -0.05
    lang
    -0.05
    abel
    -0.05
    èĤ¡
    -0.04
    us
    -0.04
     ÙĨØ´
    -0.04
    Ùĩ
    -0.04
    pty
    -0.04
     ÑĥзнаÑĤÑĮ
    -0.04
    POSITIVE LOGITS
     Perj
    0.07
    acto
    0.06
    人äºĨ
    0.06
     *–
    0.06
    ูà¸Ķ
    0.06
    ç¨įæľī
    0.06
    saan
    0.06
    اذ
    0.06
    å¸Ĥå§Ķå¸ĤæĶ¿åºľ
    0.06
    anyl
    0.06
    Activations Density 0.000%

    No Known Activations