© 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. 21018
    Prev
    Next
    INDEX
    Explanations

    if some rumors

    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
     ì§
    -0.09
    à´µ
    -0.09
    大大æıIJé«ĺ
    -0.09
    èĤĺ
    -0.08
    chod
    -0.08
    è¹ī
    -0.08
    aina
    -0.08
    åĵĩ
    -0.08
    Cla
    -0.08
    iger
    -0.08
    POSITIVE LOGITS
     ever
    0.11
    æľīä»»ä½ķ
    0.10
     EVER
    0.10
    åŃº
    0.09
    åīįæīĢ
    0.09
    èĥ½è®©
    0.09
    çļĦ話
    0.09
    èĥ½å¤Łè®©
    0.09
    人æ°Ķ
    0.09
    èĥ½
    0.08
    Activations Density 0.068%

    No Known Activations