© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18818
    Prev
    Next
    INDEX
    Explanations

    date and time formats

    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
    series
    -0.06
    çķª
    -0.06
    insen
    -0.06
     sneak
    -0.05
    repid
    -0.05
    ajang
    -0.05
    _series
    -0.05
     поÑģлед
    -0.05
    èĥ¡åŃIJ
    -0.05
    -series
    -0.05
    POSITIVE LOGITS
    è¦ģç´§
    0.06
     ske
    0.05
    ç«ĭ
    0.05
    ÑıÑģ
    0.05
     specifically
    0.05
    åijĬ
    0.05
     Pretty
    0.05
    æĪ·æĪ·
    0.05
    obe
    0.05
     sung
    0.05
    Activations Density 0.021%

    No Known Activations