© 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. 18351
    Prev
    Next
    INDEX
    Explanations

    correlation functions and statistics

    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
    å°ı家
    -0.05
     anot
    -0.05
    éľĢè¦ģåĩĨå¤ĩ
    -0.05
    ekan
    -0.05
    orgeous
    -0.05
    ìĹŃ
    -0.05
     zÅĤoż
    -0.05
     ØŃاÙĦÙĬا
    -0.05
    ela
    -0.05
     final
    -0.05
    POSITIVE LOGITS
     inher
    0.05
    lag
    0.05
    ึ
    0.05
    otland
    0.05
    iness
    0.05
    é¦ĸ
    0.05
    ince
    0.05
    haus
    0.05
     lag
    0.05
    æĩ¿
    0.05
    Activations Density 0.006%

    No Known Activations