© 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. 9978
    Prev
    Next
    INDEX
    Explanations

    take a look

    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
    UNK
    -0.10
    elsing
    -0.10
    å¼ĢéŨ
    -0.10
    åīįæıIJæĺ¯
    -0.10
    å¤ĸ表
    -0.09
    elter
    -0.09
     ÐŁÐµÑĢе
    -0.09
    ieder
    -0.09
    ching
    -0.09
    è¶ħé¢Ŀ
    -0.09
    POSITIVE LOGITS
    æĸ¹ä½į
    0.09
    çĮľ
    0.09
    رأ
    0.08
    chemist
    0.08
    needle
    0.08
    uo
    0.08
    panel
    0.08
    راÙĩ
    0.08
    æѤåĪ»
    0.08
    åIJ¬åIJ¬
    0.08
    Activations Density 0.020%

    No Known Activations