© 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. 18228
    Prev
    Next
    INDEX
    Explanations

    ability to do things

    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
    atak
    -0.05
     Cul
    -0.05
    ate
    -0.05
    éŀį
    -0.05
    /files
    -0.05
    amp
    -0.05
    å®ī
    -0.05
     PK
    -0.05
    atar
    -0.05
    æĸ½
    -0.05
    POSITIVE LOGITS
    дне
    0.07
    ãģªãĤĵãģ¨
    0.06
     FORE
    0.06
     helicopt
    0.06
    Ñģне
    0.06
    ä¸ĢåĪĩçļĦ
    0.06
     رؤ
    0.06
    壹
    0.06
    æ´»çļĦ
    0.06
    æľĢåĢ¼å¾Ĺ
    0.06
    Activations Density 0.005%

    No Known Activations