© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62519
    Prev
    Next
    INDEX
    Explanations

    operations and cleanup

    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
    ä¹ŀ
    -0.10
    rag
    -0.08
    éĹ´éļĶ
    -0.08
    isen
    -0.08
    èµĦ
    -0.08
    åĶ¤
    -0.08
    isons
    -0.08
    plug
    -0.08
    ä¹łæĥ¯
    -0.08
    appen
    -0.08
    POSITIVE LOGITS
    æģ¢å¤įæŃ£å¸¸
    0.14
    尽快
    0.13
    æģ¢å¤į
    0.13
    æ¸ħçIJĨ
    0.12
    ä¿®å¤į
    0.12
    æݪæĸ½
    0.11
    çİ°éĺ¶æ®µ
    0.11
    å°½åı¯èĥ½
    0.10
    å°½æĹ©
    0.10
    çı¾åł´
    0.10
    Activations Density 0.054%

    No Known Activations