© 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. 19827
    Prev
    Next
    INDEX
    Explanations

    include or contain

    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
     sub
    -0.05
    оÑģÑĥ
    -0.05
    ืà¹Īà¸Ļ
    -0.05
    çĸ¾
    -0.05
     subj
    -0.05
    äºİæĺ¯åľ¨
    -0.05
    åİĦ
    -0.05
     len
    -0.05
    кÑĢов
    -0.05
    rÃŃ
    -0.05
    POSITIVE LOGITS
    æĺİçĻ½
    0.06
    ä¸ĵä¸ļçŁ¥è¯Ĩ
    0.06
    èĶ¼
    0.06
    ella
    0.05
    æt
    0.05
    andingkan
    0.05
    丽çļĦ
    0.05
    ijing
    0.05
    adr
    0.05
    |array
    0.05
    Activations Density 0.001%

    No Known Activations