© 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. 36755
    Prev
    Next
    INDEX
    Explanations

    went on 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
    åıĤ
    -0.10
    å°±è¿Ļä¹Ī
    -0.10
    ä¸İæŶ
    -0.10
    _INLINE
    -0.09
    æīĵå¾Ĺ
    -0.09
    æĥķ
    -0.08
    igan
    -0.08
    ç»´å°Ķ
    -0.08
    æĢİä¹ĪåĽŀäºĭ
    -0.08
    æ¼³
    -0.08
    POSITIVE LOGITS
    éļıåIJİ
    0.27
     subsequently
    0.19
    åIJİç»Ń
    0.19
     subsequent
    0.19
    æѤåIJİ
    0.19
    æİ¥ä¸ĭæĿ¥
    0.18
    ãģĿãģ®å¾Į
    0.18
    ä¹ĭåIJİ
    0.17
    ç´§æİ¥çĿĢ
    0.17
    åIJİæĿ¥
    0.17
    Activations Density 0.095%

    No Known Activations