© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35960
    Prev
    Next
    INDEX
    Explanations

    DC motor, BLDC, wheel rotations

    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
    lopen
    -0.09
    ç³ľ
    -0.09
    -fw
    -0.09
    ä½ŀ
    -0.09
    æĭľ
    -0.09
    åŀĽ
    -0.09
    ç´§
    -0.09
    lio
    -0.09
    DMA
    -0.09
    赶
    -0.09
    POSITIVE LOGITS
    8
    0.10
    9
    0.10
    æİĪæĿĥ
    0.10
    3
    0.10
    0
    0.10
    2
    0.09
     Atlantic
    0.09
    头åıij
    0.09
    4
    0.09
    çĶµæľº
    0.09
    Activations Density 0.098%

    No Known Activations