© 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. 21079
    Prev
    Next
    INDEX
    Explanations

    political leaders' names

    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
     sat
    -0.05
     princip
    -0.05
    mad
    -0.05
    æĮĩæłĩçļĦ
    -0.05
     зна
    -0.05
    Paths
    -0.05
    è¹ĭ
    -0.05
     K
    -0.05
    воÑĢ
    -0.04
    ede
    -0.04
    POSITIVE LOGITS
    alp
    0.06
    ä½Ĩæĺ¯å¦Ĥæŀľ
    0.06
    æ¯ķç«Łæĺ¯
    0.06
    çİ°åľ¨æĪij
    0.06
    尼奥
    0.06
     permane
    0.06
    วà¸Ļ
    0.06
     جÙĬر
    0.06
    ecd
    0.06
    æ¶ī
    0.06
    Activations Density 0.076%

    No Known Activations