© 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. 18604
    Prev
    Next
    INDEX
    Explanations

    lists of characters or names

    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
    usch
    -0.06
     waarop
    -0.05
    å¤ĸç·ļ
    -0.05
    enne
    -0.05
    vak
    -0.05
    iffer
    -0.05
    çļĦçĶŁæ´»
    -0.05
    çļĦçĶŁæ´»æĸ¹å¼ı
    -0.05
     hem
    -0.05
    union
    -0.05
    POSITIVE LOGITS
    оÑģÑĮ
    0.06
    å¿łå®ŀ
    0.05
    ogg
    0.05
     Accom
    0.05
    pec
    0.05
    -by
    0.05
    ä¸įæģ¯
    0.05
     afer
    0.05
    бÑĥ
    0.05
    lds
    0.05
    Activations Density 0.002%

    No Known Activations