© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57934
    Prev
    Next
    INDEX
    Explanations

    names and names parts

    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
    igmoid
    -0.10
    天èĬ±æĿ¿
    -0.09
    åħļå»ºå·¥ä½ľ
    -0.09
    两ä¼ļ
    -0.09
    ä¸Ĭæµ·å¸Ĥ
    -0.09
    orp
    -0.08
    pling
    -0.08
     Illinois
    -0.08
     życ
    -0.08
    çªį
    -0.08
    POSITIVE LOGITS
    çģ«åĬĽ
    0.09
     mest
    0.09
    æİĪ
    0.09
    ember
    0.09
    ä¿®
    0.08
    çī§
    0.08
    SearchParams
    0.08
    gle
    0.08
    iju
    0.08
    çĤī
    0.08
    Activations Density 0.038%

    No Known Activations