© 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. 37119
    Prev
    Next
    INDEX
    Explanations

    nuclear followed by medical, science, or weapons

    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
    交ä¼ļ
    -0.11
    anie
    -0.10
    оваÑĢ
    -0.10
    éĻIJãĤĬ
    -0.10
    -produ
    -0.09
    æ´İ
    -0.09
    -Jul
    -0.09
    entially
    -0.09
    æĭĪ
    -0.09
    orary
    -0.09
    POSITIVE LOGITS
    ized
    0.13
    ization
    0.11
    èĭ·
    0.09
    请æĤ¨
    0.09
    ity
    0.09
    vey
    0.09
    izable
    0.08
    less
    0.08
    ials
    0.08
    à¸ĩาà¸Ļ
    0.08
    Activations Density 0.020%

    No Known Activations