© 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. 18211
    Prev
    Next
    INDEX
    Explanations

    popular, leading, common, top, main

    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
    iale
    -0.06
    ño
    -0.06
    COME
    -0.05
     lev
    -0.05
    èĤ¾çĤİ
    -0.05
    ä¸Ģ年级
    -0.05
    adium
    -0.05
    ños
    -0.05
    ien
    -0.05
    ero
    -0.05
    POSITIVE LOGITS
    ÙĪاع
    0.07
    ampo
    0.06
     Ù¾ÙĪØ´
    0.06
    еÑĩ
    0.06
    elts
    0.06
    paralleled
    0.05
    czes
    0.05
    ÑĢак
    0.05
    biz
    0.05
    typings
    0.05
    Activations Density 0.066%

    No Known Activations