© 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. 17505
    Prev
    Next
    INDEX
    Explanations

    food ingredients or financial amounts

    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
     intended
    -0.05
    fa
    -0.05
    ara
    -0.05
    onis
    -0.05
     rist
    -0.05
    allet
    -0.05
     con
    -0.05
     col
    -0.05
    å®ľäºº
    -0.04
     kol
    -0.04
    POSITIVE LOGITS
    izas
    0.08
    qü
    0.06
    entos
    0.06
    actics
    0.06
    ött
    0.06
    amenta
    0.06
    ì¹ĺê³ł
    0.06
    å¹´æĬ¥
    0.06
    ãģ¤ãģĦ
    0.06
    asuring
    0.06
    Activations Density 0.003%

    No Known Activations