© 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. 19808
    Prev
    Next
    INDEX
    Explanations

    forwarded message original code

    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
    ä¹ĭå®Ŀ
    -0.07
    æIJª
    -0.06
    anggapi
    -0.06
    enberg
    -0.06
    upro
    -0.06
    æľī声
    -0.06
     ÙĪرئÙĬس
    -0.06
     беÑĢÑĥ
    -0.06
    apé
    -0.06
    ç²īä¸Ŀ们
    -0.06
    POSITIVE LOGITS
     rel
    0.05
    les
    0.05
    0.05
    TC
    0.05
    ä»ķ
    0.05
    æĮŁ
    0.05
    ores
    0.05
    S
    0.05
    åıĶ
    0.05
    ODY
    0.05
    Activations Density 0.006%

    No Known Activations