© 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. 20899
    Prev
    Next
    INDEX
    Explanations

    dataframe assignments

    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
    ä¸įè´Łè´£
    -0.06
    ownt
    -0.06
    å·¨
    -0.06
     phóng
    -0.06
    ipeg
    -0.06
    ÙĨدÙĩ
    -0.06
    æŃ¤äºº
    -0.05
    audi
    -0.05
    Ñĸб
    -0.05
    åįĬ个
    -0.05
    POSITIVE LOGITS
     Duy
    0.05
     pa
    0.05
    è´Ŀå°Ķ
    0.05
    æ°
    0.05
    çĪ±ä¸½ä¸Ŀ
    0.05
    abel
    0.05
     equivoc
    0.05
     bel
    0.05
    ui
    0.05
    éal
    0.05
    Activations Density 0.009%

    No Known Activations