© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9627
    Prev
    Next
    INDEX
    Explanations

    spreading concepts or ideas

    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
     hÆ°á»Łng
    -0.10
    åĶı
    -0.09
    ä¸Ģ代
    -0.09
    åĢĻ
    -0.09
    å¹½
    -0.08
     shampoo
    -0.08
    髦
    -0.08
     Contributor
    -0.08
     View
    -0.08
    毫
    -0.08
    POSITIVE LOGITS
    çŃĭ
    0.10
    çķĮéĻIJ
    0.09
    æĬ½æŁ¥
    0.09
    å¤ļåĬŁèĥ½
    0.09
    æľ¬æĿ¥å°±
    0.09
    æ²īéĩį
    0.09
    紧紧
    0.09
    å»ī
    0.09
    æŃ£æĸĩ
    0.09
    ASF
    0.08
    Activations Density 0.059%

    No Known Activations