© 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. 18094
    Prev
    Next
    INDEX
    Explanations

    navigation menu

    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
    代ä¼ļ
    -0.06
    æĬĬäºĭæĥħ
    -0.05
     thereof
    -0.05
    éĥ½åºĶ该
    -0.05
    .§
    -0.05
    äºĮåŃĹ
    -0.05
     Thu
    -0.05
    è´¾
    -0.05
    érés
    -0.05
     incarn
    -0.05
    POSITIVE LOGITS
    ként
    0.07
    æĪ¶
    0.06
    mer
    0.06
    ÑģÑĤÑĢа
    0.06
     Shades
    0.06
    jord
    0.06
    èİİ士æ¯Ķäºļ
    0.06
    haus
    0.06
    enced
    0.06
    ground
    0.05
    Activations Density 0.002%

    No Known Activations