© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17697
    Prev
    Next
    INDEX
    Explanations

    SQL UPDATE SET clauses

    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
    çļĦæĥħ
    -0.06
    iform
    -0.06
    enge
    -0.05
    à¸Ľà¸IJม
    -0.05
    hir
    -0.05
    ikke
    -0.05
    irse
    -0.05
    legen
    -0.05
    BW
    -0.05
    èĥļ
    -0.05
    POSITIVE LOGITS
    æĽ´æĸ°çļĦ
    0.06
    é½
    0.06
     Andal
    0.05
    æĽ´æĸ°äºĨ
    0.05
    çļĦæľĢåIJİ
    0.05
    updatedAt
    0.05
    æĽ´æĸ°
    0.05
    (updated
    0.05
    Update
    0.05
    ugin
    0.05
    Activations Density 0.007%

    No Known Activations