© 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. 20124
    Prev
    Next
    INDEX
    Explanations

    facial expressions and sensations

    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
    -0.05
     "
    -0.05
    zep
    -0.05
     jaz
    -0.05
    çĿ¡è§ī
    -0.05
    ommer
    -0.05
    temp
    -0.05
    `
    -0.05
    çļĦç¡®
    -0.05
    خت
    -0.05
    POSITIVE LOGITS
    OSO
    0.07
     rehabil
    0.06
     Presupuesto
    0.06
    ukas
    0.06
    apprend
    0.06
    agers
    0.06
    績
    0.06
     angusti
    0.06
     Ø£ÙİÙĬ
    0.06
    mä
    0.06
    Activations Density 0.017%

    No Known Activations