© 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. 19737
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    èĭ¦
    -0.06
    tus
    -0.06
    ä¿Ĭ
    -0.06
    åıªä¸º
    -0.05
    impa
    -0.05
    ä»ħ
    -0.05
    ÑĪеÑĤ
    -0.05
    attles
    -0.05
     رأس
    -0.05
     struggles
    -0.05
    POSITIVE LOGITS
    duto
    0.06
    æ¯ĶæĭŁ
    0.05
    ollen
    0.05
    enta
    0.05
    '.$
    0.05
    uvre
    0.05
    version
    0.05
    æĸ¹ãĤĤå¤ļãģĦ
    0.05
    msg
    0.05
    æľªå¤®
    0.05
    Activations Density 0.003%

    No Known Activations