© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52323
    Prev
    Next
    INDEX
    Explanations

    fiber optics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    åįĥéĩĮ
    -0.09
    sWith
    -0.09
     Monte
    -0.09
    æĿĵ
    -0.09
    manship
    -0.08
    generator
    -0.08
    rus
    -0.08
    ification
    -0.08
     announc
    -0.08
    åijĺ
    -0.08
    POSITIVE LOGITS
    less
    0.11
    ivist
    0.11
    erals
    0.10
    banks
    0.10
    天ä¸Ĭ
    0.09
     ÙħÙĩÙħ
    0.09
    asar
    0.09
    èĸ¨
    0.09
    osos
    0.09
    没éĶĻ
    0.09
    Activations Density 0.010%

    No Known Activations