© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18536
    Prev
    Next
    INDEX
    Explanations

    weather conditions and descriptions

    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
     Desert
    -0.05
    临ç»Ī
    -0.05
     nightly
    -0.05
     hottest
    -0.05
     Simple
    -0.05
    dest
    -0.05
    orus
    -0.04
    _part
    -0.04
    Simple
    -0.04
    åģľçķĻ
    -0.04
    POSITIVE LOGITS
    nus
    0.07
    enthe
    0.06
    اÙĦÙĬا
    0.06
    ekk
    0.06
    éĤĢ
    0.06
    åĨµ
    0.06
    éĤĥ
    0.06
    æ¸ħçļĦ
    0.06
    unia
    0.06
    uiten
    0.06
    Activations Density 0.015%

    No Known Activations