© 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. 35529
    Prev
    Next
    INDEX
    Explanations

    modular

    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
    æľĭåıĭ
    -0.09
    龸
    -0.08
    argo
    -0.08
    Permanent
    -0.08
    VRT
    -0.08
    èĢķåľ°
    -0.08
    procedure
    -0.08
    éĢŀ
    -0.08
    åħ¬æĬ¥
    -0.08
    elo
    -0.08
    POSITIVE LOGITS
    æ¯ı次
    0.10
     modular
    0.10
    éļ¾æĢª
    0.10
    æĢ§å¼º
    0.09
     approach
    0.09
    æĢ§åĴĮ
    0.09
    çłľ
    0.09
    大å¸Ī
    0.09
    -component
    0.09
    éĺ¶æ®µæĢ§
    0.09
    Activations Density 0.047%

    No Known Activations