© 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. 19842
    Prev
    Next
    INDEX
    Explanations

    extensive libraries and ecosystem types

    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
     اÙĦدÙĬÙĨ
    -0.11
    èĬĤ缮ä¸Ń
    -0.11
    çĸĻ
    -0.09
    é¢łè¦Ĩ
    -0.09
     ÙĪاÙĦÙĨ
    -0.09
    åī§ä¸Ń
    -0.08
    æģ¶éŃĶ
    -0.08
    ä¸įæĿ¥
    -0.08
     Sing
    -0.08
    elines
    -0.08
    POSITIVE LOGITS
    çĶŁæĢģåľĪ
    0.10
    丰å¯ĮçļĦ
    0.09
    æĪIJçĨŁçļĦ
    0.09
    åĩłä¹İæĺ¯
    0.09
    aland
    0.09
    æĤ£çĹħ
    0.09
    éĶī
    0.09
    åı¯çĶ¨
    0.08
    æĤłä¹ħ
    0.08
    Ĩµ
    0.08
    Activations Density 0.252%

    No Known Activations