© 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. 17937
    Prev
    Next
    INDEX
    Explanations

    /* comment markers

    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
    ª
    -0.08
    å°ı鹿
    -0.07
    leve
    -0.07
    ãģ£ãģįãĤĬ
    -0.07
    ÙĴÙĨ
    -0.06
    egt
    -0.06
    artal
    -0.06
    æĸĩæĺİçļĦ
    -0.06
    ÙIJ
    -0.06
    entiful
    -0.06
    POSITIVE LOGITS
     unr
    0.05
    æķĪ
    0.05
     ho
    0.05
    oth
    0.05
    å½±
    0.05
    Ñħов
    0.05
    H
    0.05
     inv
    0.05
    æĶ¾çŁ¢
    0.05
    иÑĢа
    0.05
    Activations Density 0.021%

    No Known Activations