© 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. 18804
    Prev
    Next
    INDEX
    Explanations

    names ending in man or woman

    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
    سÙĬ
    -0.06
    رب
    -0.06
     Fur
    -0.05
    ctal
    -0.05
    æĪijçļĦç¥Ŀç¦ı
    -0.05
    icha
    -0.05
    é»
    -0.05
    ear
    -0.05
    uesta
    -0.05
    Ñģили
    -0.05
    POSITIVE LOGITS
    缼
    0.06
    kopf
    0.06
    imdi
    0.06
    kre
    0.05
    anser
    0.05
     vient
    0.05
    etro
    0.05
    幸ç¦ı
    0.05
    angkan
    0.05
    å¥¢æľĽ
    0.05
    Activations Density 0.141%

    No Known Activations