© 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. 52583
    Prev
    Next
    INDEX
    Explanations

    famous people's names

    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
    åĮ»ç§ij
    -0.11
    üstü
    -0.10
    æĩĤäºĭ
    -0.10
    éģģ
    -0.10
    åį¡æĭī
    -0.10
    èĭ¦èĭ¦
    -0.09
    éļ¶å±ŀäºİ
    -0.09
    ëĭĮ
    -0.09
    æĺ¯æĪijçļĦ
    -0.09
    è¹Ħ
    -0.09
    POSITIVE LOGITS
    亲èĩª
    0.10
    4
    0.09
    6
    0.08
    è¢Ĥ
    0.08
     quart
    0.08
    dds
    0.08
    âĻ¦
    0.08
     himself
    0.08
    3
    0.08
    5
    0.08
    Activations Density 0.101%

    No Known Activations