© 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. 17626
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers

    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
    ogenic
    -0.06
    uos
    -0.06
    idos
    -0.05
    burger
    -0.05
    quis
    -0.05
    羯
    -0.05
    çļ®
    -0.05
    è¦ģåıĬæŶ
    -0.05
    pot
    -0.05
    èº
    -0.05
    POSITIVE LOGITS
    stab
    0.07
    ÐĵлавнÑĭе
    0.06
    èĢ½
    0.06
    æĹ¶å¯¹
    0.06
    ails
    0.06
    æĹ¶åľ¨
    0.06
    ëĭĺê»ĺ
    0.06
    æľĢç»ĪåıĹçĽĬ
    0.06
    amon
    0.05
    ä¸Ķåľ¨
    0.05
    Activations Density 0.059%

    No Known Activations