© 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. 21020
    Prev
    Next
    INDEX
    Explanations

    licensed, reputable, company

    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
    είο
    -0.06
    å¾Ĵ
    -0.05
     im
    -0.05
     ch
    -0.05
    ined
    -0.05
    ä¸įæľį
    -0.05
     site
    -0.05
    bus
    -0.05
    æĪIJ
    -0.05
    ä»Ĭ天
    -0.04
    POSITIVE LOGITS
     reputable
    0.07
    èĥĮ书
    0.07
    æŃ£è§ĦçļĦ
    0.07
     Established
    0.07
    gré
    0.07
     trustworthy
    0.06
     established
    0.06
    Well
    0.06
    åı¯éĿłçļĦ
    0.06
    à¹Ģà¸ļืà¹īà¸Ńà¸ĩ
    0.06
    Activations Density 0.023%

    No Known Activations