© 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. 20796
    Prev
    Next
    INDEX
    Explanations

    Sumerian Gilgamesh Clarke human

    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
    éĹŃ
    -0.06
    å°±åľ°
    -0.05
    ×ķ×ijר
    -0.05
    æijĨ
    -0.05
    obel
    -0.05
     bedding
    -0.05
    çĬĢ
    -0.05
    æį®
    -0.05
    chal
    -0.05
    è¿ŀ
    -0.05
    POSITIVE LOGITS
    çĭ¬è§Ĵ
    0.06
    encie
    0.06
    çļĦäºĭ
    0.06
     Worship
    0.06
    æĿ¡æĿ¡
    0.05
    åıĮåĢį
    0.05
    ê³Ħìķ½
    0.05
    å¼Ģ票
    0.05
    (case
    0.05
     Oil
    0.05
    Activations Density 0.006%

    No Known Activations