© 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. 21357
    Prev
    Next
    INDEX
    Explanations

    letters to the editor or comments

    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
     Ñįлем
    -0.06
    usas
    -0.06
    audi
    -0.06
    åı£å¤´
    -0.06
    ä¸Ńçݯ
    -0.06
    å®ĥ们æĺ¯
    -0.06
    å±±ä¸Ń
    -0.06
    æĬ¥å¯¼
    -0.06
    æķĻ主
    -0.06
    èĬĤèĬĤ
    -0.06
    POSITIVE LOGITS
    æĥ³åĪ°çļĦ
    0.05
     homog
    0.05
    ross
    0.05
    èį£åįİ
    0.05
    对çŃĸ
    0.05
     contributions
    0.05
     viewBox
    0.05
    ombe
    0.05
    lyn
    0.05
    utan
    0.05
    Activations Density 0.141%

    No Known Activations