© 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. 18582
    Prev
    Next
    INDEX
    Explanations

    celebrations, dates, or events

    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
    )'),
    -0.06
    åIJģ
    -0.06
    ä¸İç»´æĬ¤
    -0.06
    说æľī
    -0.06
    rez
    -0.05
    mith
    -0.05
    æŁĴ
    -0.05
    ulas
    -0.05
    çĥĪçļĦ
    -0.05
    åĴĮç»´æĬ¤
    -0.05
    POSITIVE LOGITS
    ateral
    0.05
    ljan
    0.05
     KIND
    0.05
    gili
    0.05
    .generic
    0.05
    çīĪ
    0.05
    eness
    0.05
    åĩºäºĨä¸Ģ
    0.05
    atty
    0.05
     leading
    0.05
    Activations Density 0.001%

    No Known Activations