© 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. 19543
    Prev
    Next
    INDEX
    Explanations

    original source material

    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
    ç´¯çļĦ
    -0.06
    رÙĤ
    -0.06
    åħŃçĻ¾
    -0.06
    ä¸į大çļĦ
    -0.06
    èĤ¥å¤§
    -0.06
    ä¸Ģç²Ĵ
    -0.06
    haps
    -0.06
     пÑĢого
    -0.06
    ä¸ĥçĻ¾
    -0.06
    rolled
    -0.05
    POSITIVE LOGITS
    åŃĺåľ¨
    0.06
    åŃĺåľ¨çĿĢ
    0.06
     presence
    0.06
     Presence
    0.06
    zust
    0.06
    æľ¨åħ°
    0.05
    -e
    0.05
     constante
    0.05
    æ¯Ķçī¹
    0.05
    oks
    0.05
    Activations Density 0.001%

    No Known Activations