© 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. 21926
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    éĻIJãĤĬ
    -0.06
    ooth
    -0.05
    rais
    -0.05
    çº¢ç´ł
    -0.05
    eer
    -0.05
     ìĸ´
    -0.05
     swear
    -0.05
    åĪĨ段
    -0.05
    è´¯
    -0.05
    ئ
    -0.05
    POSITIVE LOGITS
    elter
    0.06
    cock
    0.06
    hors
    0.06
    band
    0.06
    nü
    0.06
    lec
    0.06
    çĤİçĤİ
    0.06
    à¹ĩà¸Ńà¸Ľ
    0.06
    åѦåĪĨ
    0.06
    为åģļ好
    0.06
    Activations Density 0.000%

    No Known Activations