© 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. 20190
    Prev
    Next
    INDEX
    Explanations

    building construction sequence

    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
    ute
    -0.06
    å¾Ĺä¸Ģ
    -0.05
    ÑģÑĤоÑĢ
    -0.05
    פת
    -0.05
    ilas
    -0.05
    UTE
    -0.05
     dissect
    -0.05
    ä¸įçł´
    -0.05
    Minute
    -0.05
     geograf
    -0.05
    POSITIVE LOGITS
    å®ĮæĪIJ
    0.06
     completion
    0.06
    _completion
    0.06
     Completion
    0.06
    کاÙĨ
    0.06
    writes
    0.05
    éĹ²
    0.05
    å®Įå·¥
    0.05
    oya
    0.05
    akit
    0.05
    Activations Density 0.100%

    No Known Activations