© 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. 18524
    Prev
    Next
    INDEX
    Explanations

    width values (pixels, rpx, dp)

    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
    avera
    -0.05
    uards
    -0.05
    kers
    -0.05
    ä¹İ
    -0.05
    ailles
    -0.05
    éĥ½æľīäºĨ
    -0.05
    æģ¤
    -0.05
    éĩijæĸ¯
    -0.05
    AGAIN
    -0.05
    zept
    -0.05
    POSITIVE LOGITS
    omme
    0.07
    éĢ£ãĤĮ
    0.06
    ductive
    0.06
    ellen
    0.05
     sof
    0.05
    ucing
    0.05
    anto
    0.05
    æ¸Ī
    0.05
    omm
    0.05
    ducted
    0.05
    Activations Density 0.021%

    No Known Activations