© 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. 20678
    Prev
    Next
    INDEX
    Explanations

    ranges separated by hyphen or "to"

    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
    åħ¶ä¸Ģ
    -0.06
    -
    -0.05
    èķ
    -0.05
    /current
    -0.05
    ä¸Ģç±»
    -0.05
     Protector
    -0.05
     particular
    -0.05
    ذج
    -0.05
    人说
    -0.05
    丰
    -0.05
    POSITIVE LOGITS
    Ú¯ÙĪ
    0.07
    eiro
    0.06
     "["
    0.06
    .Stage
    0.06
    "group
    0.06
     |[
    0.06
     tiên
    0.05
    èµĤ
    0.05
    à¹Īà¸Ńà¸ĩ
    0.05
     jas
    0.05
    Activations Density 0.008%

    No Known Activations