© 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. 18040
    Prev
    Next
    INDEX
    Explanations

    medical, insurance, care, energy storage

    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
    inson
    -0.06
    çĦ¶æĺ¯
    -0.06
    sworth
    -0.06
    urch
    -0.05
    mdi
    -0.05
    rej
    -0.05
    ä»·æł¼æĺ¯
    -0.05
     alike
    -0.05
    oline
    -0.05
    prec
    -0.05
    POSITIVE LOGITS
    éviter
    0.06
     дÑĥÑĪ
    0.06
    lavn
    0.06
    imest
    0.06
    deutsch
    0.05
    åľŁ
    0.05
    Cuán
    0.05
    éŃģ
    0.05
    angat
    0.05
    ä¸īçŃī
    0.05
    Activations Density 0.055%

    No Known Activations