© 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. 36898
    Prev
    Next
    INDEX
    Explanations

    dirt, blood, and stains

    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
    ä»Ģä¹Īäºĭæĥħ
    -0.11
    岫
    -0.10
    大楼
    -0.10
    éĮ¾
    -0.10
    éĶī
    -0.10
    èĩªå·±åĸľæ¬¢
    -0.10
    æ¢ĵ
    -0.09
    ä¸Ģåľº
    -0.09
    è¾ĩ
    -0.09
    åIJĮä¸ļ
    -0.09
    POSITIVE LOGITS
    æ²¾
    0.16
    éĻĦ
    0.11
    污
    0.11
    污æŁĵ
    0.10
    æ¸į
    0.10
    æīĭä¸Ĭ
    0.10
    æ±ļãĤĮ
    0.10
     residue
    0.10
    æ®ĭçķĻ
    0.10
    çĺĢ
    0.10
    Activations Density 0.160%

    No Known Activations