© 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. 18504
    Prev
    Next
    INDEX
    Explanations

    particle physics and matter

    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
    åħĢ
    -0.06
    çĶ²
    -0.06
     aug
    -0.06
    è¡Ķ
    -0.06
     liner
    -0.05
    对人çļĦ
    -0.05
     raw
    -0.05
    çĶ²æĸ¹çļĦ
    -0.05
    ACHED
    -0.05
    å·¥ç¨ĭæľīéĻIJåħ¬åı¸
    -0.05
    POSITIVE LOGITS
    渡åģĩ
    0.06
     Hunt
    0.06
     hypo
    0.06
     ÐŁÑĢедпо
    0.06
     introd
    0.06
    æŁ¥æ¼ı
    0.06
    MAS
    0.05
     speculation
    0.05
    åĪĬ
    0.05
     worthless
    0.05
    Activations Density 0.014%

    No Known Activations