© 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. 9695
    Prev
    Next
    INDEX
    Explanations

    trip to

    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¸Ģ身
    -0.10
    etes
    -0.10
    ä¸Ģç§į
    -0.09
    åĭ¤å¥ĭ
    -0.09
    æ²®
    -0.09
    修身
    -0.09
    å°ıäºĭ
    -0.09
    inium
    -0.08
    æĸĩèīº
    -0.08
    ä¸Ģå®ļçļĦ
    -0.08
    POSITIVE LOGITS
    è¶Ł
    0.10
    å²Ľ
    0.09
    /cop
    0.09
     mint
    0.09
     Stap
    0.09
    ä»İæł¹æľ¬ä¸Ĭ
    0.08
    ÑĢоб
    0.08
    /lists
    0.08
    mint
    0.08
    éŃĶ
    0.08
    Activations Density 0.033%

    No Known Activations