© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51840
    Prev
    Next
    INDEX
    Explanations

    determine feasibility or utility

    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
    å¼Ĥ
    -0.08
    åĵªæĢķ
    -0.08
    çĥĽ
    -0.07
     пÑĢоÑģ
    -0.07
    even
    -0.07
    lion
    -0.07
    é£ŀ
    -0.06
    羣
    -0.06
     transc
    -0.06
    tra
    -0.06
    POSITIVE LOGITS
    å¼Ģåıij建设
    0.09
     ÐĶмиÑĤÑĢ
    0.09
    æľīçļĦçݩ家
    0.09
     oczy
    0.09
    éĻĽä¸ĭ
    0.09
    åħħåĪĨä½ĵçݰ
    0.09
    èĮ¬
    0.09
    æĮĤéĴ©
    0.09
    éĩ
    0.09
    åıijå±ķæł¼å±Ģ
    0.09
    Activations Density 0.236%

    No Known Activations