© 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. 17586
    Prev
    Next
    INDEX
    Explanations

    Battle of, Siege of, Roman de, Wheel of

    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
    aph
    -0.07
     badan
    -0.05
     Priv
    -0.05
    ais
    -0.05
     pien
    -0.05
    eks
    -0.05
    æķĪæŀľæĽ´å¥½
    -0.05
    æľīé«ĺ
    -0.05
    uros
    -0.04
    érc
    -0.04
    POSITIVE LOGITS
    aders
    0.06
    astro
    0.06
    estos
    0.05
    ØŃدة
    0.05
    esto
    0.05
    ade
    0.05
     occupations
    0.05
    eru
    0.05
    èĢĮç«ĭ
    0.05
    utiliser
    0.05
    Activations Density 0.018%

    No Known Activations