© 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. 17920
    Prev
    Next
    INDEX
    Explanations

    on or off the field

    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
    纥
    -0.09
    çIJ®
    -0.09
    æĸ°è¥¿
    -0.09
    æīĢè°ĵçļĦ
    -0.09
    .managed
    -0.09
    ç§Ģ
    -0.09
    åĬ¿åĬĽ
    -0.09
    ä¸įåıĬ
    -0.09
     DIRECTORY
    -0.08
    饺
    -0.08
    POSITIVE LOGITS
    课åłĤ
    0.14
     classroom
    0.12
    æķĻ室
    0.11
    æĪĺåľº
    0.10
    æĪĺåľºä¸Ĭ
    0.10
    åłĤ
    0.10
    ä½ľä¸ļ
    0.09
    åĨħå¤ĸ
    0.09
    åı°ä¸Ĭ
    0.09
     Vanity
    0.09
    Activations Density 0.115%

    No Known Activations