© 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. 19981
    Prev
    Next
    INDEX
    Explanations

    equality

    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
    òi
    -0.07
    edList
    -0.06
    (es
    -0.06
    вален
    -0.06
    fulness
    -0.05
    ÙĩÙħا
    -0.05
    åĩĮ
    -0.05
    ings
    -0.05
    eds
    -0.05
    recision
    -0.05
    POSITIVE LOGITS
    arani
    0.06
    as
    0.06
     inför
    0.06
    utton
    0.05
    æľīçĶ¨çļĦ
    0.05
    è®®ä¼ļ
    0.05
    оле
    0.05
     interes
    0.05
    éĽĦå¿ĥ
    0.05
    .Convert
    0.05
    Activations Density 0.004%

    No Known Activations