© 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. 19961
    Prev
    Next
    INDEX
    Explanations

    Royalty, Early, Winter, Purpose, Geography, Biography, Long

    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
    više
    -0.06
    为ä»Ģä¹Īè¦ģ
    -0.06
    建议
    -0.06
    ãĥŁãĥį
    -0.06
    mach
    -0.05
    为ä½ķ
    -0.05
    нÑĥÑĤÑĮÑģÑı
    -0.05
     why
    -0.05
    Ñĥд
    -0.05
    æĥ¯äºĨ
    -0.05
    POSITIVE LOGITS
    ock
    0.07
    _sdk
    0.06
    lja
    0.06
    âĢ¦,
    0.06
    гол
    0.05
    daftar
    0.05
    {\"
    0.05
    bs
    0.05
    ielt
    0.05
    åħīæĺ¯
    0.05
    Activations Density 0.022%

    No Known Activations