© 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. 18773
    Prev
    Next
    INDEX
    Explanations

    current date or time

    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
    éļ
    -0.05
    itect
    -0.05
     "
    -0.05
    -0.05
    个人
    -0.05
    Luckily
    -0.05
    uid
    -0.04
    æºIJåľ°
    -0.04
    èªĮ
    -0.04
     Manual
    -0.04
    POSITIVE LOGITS
    éch
    0.07
    ensem
    0.07
    olem
    0.07
    obra
    0.07
    лÑİби
    0.07
    ä¸įåħ¥
    0.06
    бок
    0.06
    ughter
    0.06
    lech
    0.06
    pleri
    0.06
    Activations Density 0.005%

    No Known Activations