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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37128
    Prev
    Next
    INDEX
    Explanations

    favorite / favourite

    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
    è¦ģæ¯Ķ
    -0.10
    ä¹ĥ
    -0.09
    _dbg
    -0.09
    è·ijéģĵ
    -0.08
     abb
    -0.08
     PAS
    -0.08
    å»¶æľŁ
    -0.08
    åħ±åIJĮä½ĵ
    -0.08
    esson
    -0.08
    _IA
    -0.08
    POSITIVE LOGITS
    eting
    0.09
    ãĥľãĥ¼ãĥī
    0.09
    æĺ¯å¯¹
    0.09
    éĽĴ
    0.09
    -worthy
    0.09
    å¿ĥ头
    0.09
    ä¸įæĥľ
    0.09
    ableObject
    0.08
    ç¿ķ
    0.08
    åĪĨæµģ
    0.08
    Activations Density 0.018%

    No Known Activations