© 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. 17536
    Prev
    Next
    INDEX
    Explanations

    physical things and states

    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
    eceÄŁi
    -0.07
    اء
    -0.06
    wiÄĻ
    -0.06
    ä¸įçĶŁ
    -0.05
    adop
    -0.05
    kaar
    -0.05
    ebilecek
    -0.05
     refres
    -0.05
    OTH
    -0.05
    å»ī
    -0.05
    POSITIVE LOGITS
    ÃŃce
    0.05
    ently
    0.05
    åĴĮçĻ½
    0.05
    imeline
    0.05
    å¼±
    0.05
    imli
    0.05
     et
    0.05
    é¾Ł
    0.05
    çļĦå°±æĺ¯
    0.05
    å°ī
    0.05
    Activations Density 0.071%

    No Known Activations