© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 20813
    Prev
    Next
    INDEX
    Explanations

    bands and musicians

    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
     Nap
    -0.10
    温室
    -0.10
    è½½ä½ĵ
    -0.09
    æIJ¦
    -0.09
    轸
    -0.09
    å¢ĺ
    -0.09
    æĻ¯å¾·
    -0.09
    éĩįéĩį
    -0.08
    åĺīå¹´åįİ
    -0.08
    åĸľå¥½
    -0.08
    POSITIVE LOGITS
    è¿Ń
    0.09
    roma
    0.08
    飫
    0.08
    åī
    0.08
    è·º
    0.08
    èį¯
    0.08
     Pist
    0.08
    imit
    0.08
    æľĢéĩįè¦ģ
    0.08
    è¹ĭ
    0.08
    Activations Density 0.006%

    No Known Activations