© 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. 19959
    Prev
    Next
    INDEX
    Explanations

    proposed methods and structures

    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
    åĢį
    -0.05
    inds
    -0.05
    à¥ĭà¤Ĥ
    -0.05
    è¡Ĩ
    -0.05
    hazi
    -0.05
    inar
    -0.05
    ly
    -0.05
    OR
    -0.05
     Field
    -0.05
    ä¸įèĥ½å®Įåħ¨
    -0.04
    POSITIVE LOGITS
    ائب
    0.06
    ÑĤили
    0.06
     demonstr
    0.06
     sani
    0.06
    ]|[
    0.06
    aghan
    0.06
    主æĮģåı¬å¼Ģ
    0.06
    dge
    0.06
     trÃło
    0.06
    æĸ°çŁ¥
    0.06
    Activations Density 0.109%

    No Known Activations