© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 36820
    Prev
    Next
    INDEX
    Explanations

    Watts, Volts, Amps

    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
    稿
    -0.12
    ckett
    -0.09
    çĹĩ
    -0.09
    essa
    -0.09
    çβ
    -0.08
    ../../../
    -0.08
    ugar
    -0.08
    _ENSURE
    -0.08
    CTION
    -0.08
    oder
    -0.08
    POSITIVE LOGITS
    个å¤ļ
    0.10
    smith
    0.10
    itude
    0.10
    æıĨ
    0.10
    itud
    0.10
    ted
    0.10
    侯
    0.09
    aneously
    0.09
    preter
    0.09
    ages
    0.09
    Activations Density 0.018%

    No Known Activations