© 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. 17344
    Prev
    Next
    INDEX
    Explanations

    swallowing, swamps, swanky

    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
    inten
    -0.07
     compac
    -0.07
    ationship
    -0.07
    ched
    -0.07
    urie
    -0.07
    itude
    -0.07
    gether
    -0.07
      ↵  ↵
    -0.06
    apid
    -0.06
    uria
    -0.06
    POSITIVE LOGITS
    es
    0.08
    ed
    0.07
    знаÑĩ
    0.07
    ypsy
    0.06
    s
    0.06
    رÙģ
    0.06
    æĪĸå¤ļ个
    0.06
    в
    0.06
    سبب
    0.06
    aruh
    0.05
    Activations Density 0.015%

    No Known Activations