© 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. 20992
    Prev
    Next
    INDEX
    Explanations

    founder of

    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
    ing
    -0.07
    ../../../
    -0.06
    iod
    -0.05
     Headquarters
    -0.05
    ste
    -0.05
    ble
    -0.05
     Komm
    -0.05
    곡
    -0.05
    ih
    -0.05
    æł·æĿ¿éĹ´
    -0.05
    POSITIVE LOGITS
    fran
    0.07
    olato
    0.06
    åħ´åįİ
    0.06
    ÃŃgu
    0.06
     furthermore
    0.06
    áºŃy
    0.06
    orten
    0.06
    kej
    0.06
    aries
    0.05
     cier
    0.05
    Activations Density 0.019%

    No Known Activations