© 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. 18546
    Prev
    Next
    INDEX
    Explanations

    following specific sequences

    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
    ting
    -0.05
    iz
    -0.05
    ont
    -0.05
    ound
    -0.05
    éĢı
    -0.05
    affle
    -0.05
    纵横
    -0.05
    éĥijéĩį
    -0.05
    顯
    -0.05
     Mimo
    -0.05
    POSITIVE LOGITS
    äºĮ度
    0.06
    äºĮ代
    0.06
    ç«¥å¿ĥ
    0.06
    幸åŃĺèĢħ
    0.06
    Õ»
    0.06
    åĬłåĪĨ
    0.06
    åĴĮçĶ°
    0.05
    ssc
    0.05
    ÙģرÙĨ
    0.05
    ìĸ´ìĦľ
    0.05
    Activations Density 0.004%

    No Known Activations