© 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. 36608
    Prev
    Next
    INDEX
    Explanations

    arrangements for

    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
    对æѤ
    -0.10
    æ§Ľ
    -0.10
    äºĭåIJİ
    -0.09
    缩水
    -0.09
    æ²Ļé¾Ļ
    -0.09
    糸
    -0.09
     ìĿ´ë¥¼
    -0.09
    è·»
    -0.09
    岬
    -0.08
    isse
    -0.08
    POSITIVE LOGITS
    ç¼ij
    0.09
    人çĶŁ
    0.09
    nof
    0.08
     All
    0.08
    fuse
    0.08
    人çĶŁçļĦ
    0.08
    çļĦ人çĶŁ
    0.08
    Solo
    0.08
    hest
    0.07
    çĺł
    0.07
    Activations Density 0.707%

    No Known Activations