© 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. 35136
    Prev
    Next
    INDEX
    Explanations

    biofuel types

    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
    人大
    -0.09
    æķ¬ä¸ļ
    -0.08
    åĮł
    -0.08
    åIJĥè¿ĩ
    -0.08
    è¿«åĪĩ
    -0.08
    æīĵçĶµè¯Ŀ
    -0.08
    yon
    -0.08
    aven
    -0.08
     expert
    -0.08
     flour
    -0.08
    POSITIVE LOGITS
    çĩĥæĸĻ
    0.11
    æ²¹èĦĤ
    0.11
    çĩĥæ²¹
    0.11
    èĬĹ
    0.10
    油价
    0.10
    èĮħ
    0.10
    æ²¹
    0.10
     oil
    0.10
    æľºæ²¹
    0.09
    æľīæĦıæĢĿçļĦ
    0.09
    Activations Density 0.050%

    No Known Activations