© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19699
    Prev
    Next
    INDEX
    Explanations

    groups or categories

    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
     mainly
    -0.06
     neither
    -0.05
     Fid
    -0.05
     mostly
    -0.05
    çIJ¦
    -0.05
    ven
    -0.05
    orama
    -0.05
    çĪµ
    -0.05
    主è¦ģ为
    -0.05
    ç«ĭ足
    -0.05
    POSITIVE LOGITS
    èĢĮéĿŀ
    0.06
    æ¯Ķ以å¾Ģ
    0.06
    erca
    0.06
     anz
    0.06
    iszt
    0.05
    ä¸Ĭä¸İ
    0.05
    æĽ´æľī
    0.05
    emmän
    0.05
    èĢĮä¸įæĺ¯
    0.05
    æ¯Ķ以åīį
    0.05
    Activations Density 0.032%

    No Known Activations