© 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. 51816
    Prev
    Next
    INDEX
    Explanations

    quilts

    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
    æ®ĸ
    -0.09
    æľįåĬ¡æ°´å¹³
    -0.08
    ewear
    -0.08
    æµħ
    -0.08
    çĮ¥
    -0.08
    bie
    -0.08
    åºŃ
    -0.08
    że
    -0.08
    åıijæĸĩ
    -0.08
    ä¹Ĵä¹ĵçIJĥ
    -0.08
    POSITIVE LOGITS
    /oct
    0.09
    å¤§èµĽ
    0.09
     PATCH
    0.08
    éĺ²æĻĴ
    0.08
    HITE
    0.08
    åĹľ
    0.08
    åľĪ
    0.08
     vern
    0.08
    大çĪ·
    0.08
    缺
    0.08
    Activations Density 0.004%

    No Known Activations