© 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. 21391
    Prev
    Next
    INDEX
    Explanations

    all columns, correct translation, check mark

    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
    éĿłåīį
    -0.07
    bove
    -0.07
    ä¸Ĭ好
    -0.06
    biz
    -0.06
    ualan
    -0.06
    ita
    -0.06
     سÙĬÙħا
    -0.06
    ä»Ģä¹Īäºĭ
    -0.06
    atrib
    -0.06
    æ¯Ķäºļ
    -0.06
    POSITIVE LOGITS
    æľ¬æĿ¥
    0.06
     اÙĦÙĪا
    0.06
     tá
    0.05
     obvious
    0.05
    æľ¬æĿ¥å°±æĺ¯
    0.05
    èĻ«
    0.05
     resemblance
    0.05
    åIJįåī¯åħ¶å®ŀ
    0.05
    éķ¿çĽ¸
    0.05
    ัà¸Ķ
    0.05
    Activations Density 0.003%

    No Known Activations