© 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. 17101
    Prev
    Next
    INDEX
    Explanations

    lists and analyzes information

    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
    vel
    -0.06
    Õ¡Öģ
    -0.06
     ze
    -0.06
    人åķĬ
    -0.06
    eldes
    -0.06
    ãĤĦãģ¯ãĤĬ
    -0.06
    ÑĪна
    -0.06
     Deal
    -0.05
    zzi
    -0.05
    åİ»äºĨ解
    -0.05
    POSITIVE LOGITS
    èī¯
    0.06
    çĮĸ
    0.06
    aurus
    0.05
    èĭŁ
    0.05
    åĪ®
    0.05
    con
    0.05
     solic
    0.05
    æĩĩ
    0.05
    éĩįéļ¾çĤ¹
    0.05
    ãĤ«ãĤ¿
    0.05
    Activations Density 0.045%

    No Known Activations