© 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. 20313
    Prev
    Next
    INDEX
    Explanations

    I am

    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
    а
    -0.07
    ablish
    -0.06
     latter
    -0.06
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.06
    ive
    -0.05
    orer
    -0.05
    มà¸Ļ
    -0.05
    Ãło
    -0.05
    ãĥĭãĤ¢
    -0.05
    ral
    -0.05
    POSITIVE LOGITS
    åĽŀäºĭ
    0.08
    çĦ¶å¤§
    0.07
    个å°ı
    0.07
    ir
    0.07
    ethyst
    0.07
    à¸Ľà¹Ģà¸Ķà¸ķ
    0.06
    кнÑĥÑĤÑĮ
    0.06
    éĽĨåħ¨
    0.06
    ikor
    0.06
    zia
    0.06
    Activations Density 0.055%

    No Known Activations