© 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. 17319
    Prev
    Next
    INDEX
    Explanations

    press and PR announcements

    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
    EST
    -0.05
    èĺ
    -0.05
    ç²Ĵ
    -0.05
    ä»ĸ人
    -0.05
    éŃĶçİĭ
    -0.05
    UCT
    -0.05
    weed
    -0.05
    ÐļТ
    -0.05
    enc
    -0.05
    è¸Ĭ
    -0.05
    POSITIVE LOGITS
    åĽ¢åĽ¢
    0.07
    hoot
    0.06
    ushi
    0.06
     Neutral
    0.06
    ÑĪÑĤа
    0.06
    Events
    0.06
    มวลà¸Ĭà¸Ļ
    0.06
    allback
    0.06
    éĢļãĤĬ
    0.06
    Neutral
    0.06
    Activations Density 0.041%

    No Known Activations