© 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. 9316
    Prev
    Next
    INDEX
    Explanations

    new levels, dimensions, or meaning

    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
    æį¢æĿ¥
    -0.10
    çĻ½çĻ½
    -0.08
    é£
    -0.08
    æĹ¶æľº
    -0.08
    ro
    -0.08
    noch
    -0.08
    满满
    -0.08
    缸åħ³æĶ¿çŃĸ
    -0.08
    çĴIJ
    -0.08
    ä¸ĢåĪĢ
    -0.08
    POSITIVE LOGITS
    èĮĥçķ´
    0.10
    ayers
    0.09
    gro
    0.09
    éĩįè¦ģæĦıä¹ī
    0.09
    AKER
    0.09
    SelectedItem
    0.09
    IELD
    0.09
    çļĦæĦŁåıĹ
    0.09
    åºIJ
    0.09
    åĪĨæµģ
    0.09
    Activations Density 0.012%

    No Known Activations