© 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. 18000
    Prev
    Next
    INDEX
    Explanations

    model

    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
    çĮĽåħ½
    -0.06
    亲æīĭ
    -0.06
    çķªç¦ºåĮº
    -0.05
    embro
    -0.05
    üssen
    -0.05
     Arsenal
    -0.05
    ä¼ı
    -0.05
     ÙĪØ£Ùĥثر
    -0.05
    richt
    -0.05
    sonian
    -0.05
    POSITIVE LOGITS
    éĩĩ
    0.06
    æ±Ĥæĺ¯
    0.06
    oczy
    0.06
    模çī¹
    0.06
    klar
    0.05
    çķħéĢļ
    0.05
    tul
    0.05
    züge
    0.05
    mata
    0.05
    ÙĦس
    0.05
    Activations Density 0.015%

    No Known Activations