© 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. 8912
    Prev
    Next
    INDEX
    Explanations

    reporting verbs

    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
    earch
    -0.09
    æķ´é¡¿
    -0.09
    tro
    -0.09
    èĢ¨
    -0.08
    æĩĪ
    -0.08
    sei
    -0.08
    è·¸
    -0.08
    hosts
    -0.08
    åĢ¦
    -0.08
    æİł
    -0.08
    POSITIVE LOGITS
    代表
    0.11
    åĽ¢ä½ĵ
    0.10
    åij¼åIJģ
    0.10
    社ä¼ļç»Ħç»ĩ
    0.09
    ç«ĭåį³
    0.09
    ç»´æĿĥ
    0.09
    è¯īæ±Ĥ
    0.09
     обÑĢаÑī
    0.09
    æĢ»éĥ¨
    0.08
     activists
    0.08
    Activations Density 0.074%

    No Known Activations