© 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. 22236
    Prev
    Next
    INDEX
    Explanations

    driven by

    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
    odom
    -0.11
     Stevens
    -0.10
    ÑĤиÑĢ
    -0.09
    笳
    -0.09
    çıŀ
    -0.08
    .online
    -0.08
    æĨ¬
    -0.08
    éģĩéļ¾
    -0.08
    ibase
    -0.08
    è¢ĭåŃIJ
    -0.08
    POSITIVE LOGITS
    驱åĬ¨
    0.14
     driven
    0.13
    åĬ¨åĬĽ
    0.13
    驱
    0.13
    å¸ĤåľºéľĢæ±Ĥ
    0.12
    Driven
    0.11
    åĬ¨æľº
    0.11
    -driven
    0.11
    åįģ足
    0.10
    çļĦåĬ¨åĬĽ
    0.10
    Activations Density 0.057%

    No Known Activations