© 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. 22016
    Prev
    Next
    INDEX
    Explanations

    means "smell of horse", vigor and strength

    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
    æŃ»çļĦ
    -0.06
    sis
    -0.06
    å¸Ī表
    -0.05
    oun
    -0.05
     Äijá»Ŀi
    -0.05
    æ´»çĿĢ
    -0.05
    ä¸İåħ±
    -0.05
    |null
    -0.05
    åѤåįķ
    -0.05
    åĩ
    -0.05
    POSITIVE LOGITS
    udo
    0.06
    fato
    0.06
    orde
    0.06
    žen
    0.06
    лаÑĤа
    0.06
    strtolower
    0.05
    bym
    0.05
    -Sah
    0.05
    第ä¸Ģ款
    0.05
    gow
    0.05
    Activations Density 0.031%

    No Known Activations