© 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. 20859
    Prev
    Next
    INDEX
    Explanations

    learning from children or animals

    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
     indentation
    -0.06
    หà¹Īวà¸ĩ
    -0.06
    å¿ĥçIJĨåĩĨå¤ĩ
    -0.06
    ölt
    -0.06
    iffin
    -0.06
     promis
    -0.05
    ellis
    -0.05
    ouvrez
    -0.05
     Ø°ÙĬ
    -0.05
    SIGN
    -0.05
    POSITIVE LOGITS
    éĢ¼
    0.07
    åĢĴéĢ¼
    0.07
     تد
    0.07
    迫使
    0.06
    ture
    0.06
    scr
    0.05
    adel
    0.05
    被éĢ¼
    0.05
    æij©
    0.05
    çĿ£ä¿ĥ
    0.05
    Activations Density 0.076%

    No Known Activations