© 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. 20565
    Prev
    Next
    INDEX
    Explanations

    McCormack, McCade, McCann

    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
    ../
    -0.16
    çĦ¶æĺ¯
    -0.13
    azon
    -0.11
    ãģĤãģ¾ãĤĬ
    -0.11
    ëĭ¤ê°Ģ
    -0.10
    çľģæĶ¿åºľ
    -0.09
     khá»ıi
    -0.09
    ifying
    -0.09
    ãģĤãģ®
    -0.09
    iller
    -0.09
    POSITIVE LOGITS
    ings
    0.11
    ¤
    0.10
    ers
    0.10
    rary
    0.10
    å¦ĥ
    0.10
    apped
    0.09
    wick
    0.09
    rie
    0.09
    è§Ī
    0.09
    lesia
    0.09
    Activations Density 0.147%

    No Known Activations