© 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. 10357
    Prev
    Next
    INDEX
    Explanations

    ENCODE Project

    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
    笳
    -0.09
    å¤ĦåĪĨ
    -0.09
    åĦ¿
    -0.08
    avic
    -0.08
    é¡»
    -0.08
    ä¼łç»ŁçļĦ
    -0.08
    ihan
    -0.08
    ì²ĺ리
    -0.08
    à¹Ĩ
    -0.08
    _KERNEL
    -0.08
    POSITIVE LOGITS
     project
    0.11
    ç³»åĪĹ
    0.11
    é¡¹çĽ®
    0.10
     пÑĢоекÑĤ
    0.10
    é¡¹çĽ®çļĦ
    0.10
    ãĥĹãĥŃãĤ¸ãĤ§ãĤ¯ãĥĪ
    0.10
    æijŀ
    0.09
    éłħ缮
    0.09
    ç³»åĪĹ产åĵģ
    0.09
    æĥłåıĬ
    0.09
    Activations Density 0.116%

    No Known Activations