© 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. 20837
    Prev
    Next
    INDEX
    Explanations

    leaving behind a trail

    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
    letcher
    -0.07
    ев
    -0.06
    ä¸İæĸ°
    -0.06
    ä¹īçļĦ
    -0.06
    аÑģÑĭ
    -0.06
    erio
    -0.06
    å¯¹æľªæĿ¥
    -0.06
    abis
    -0.06
    bsite
    -0.06
    ç«ĻåĪ°
    -0.05
    POSITIVE LOGITS
    è¾Ļ
    0.06
    inger
    0.05
    ież
    0.05
    ä¼ı
    0.05
    è´¹
    0.05
    ener
    0.05
    çķĻ
    0.05
    èĥľ
    0.05
    udes
    0.05
     cher
    0.05
    Activations Density 0.003%

    No Known Activations