© 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. 20029
    Prev
    Next
    INDEX
    Explanations

    words ending in -ber, -er, -mer

    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
     COMMENTS
    -0.10
    æĺ¯ä¸Ģ项
    -0.09
    zimmer
    -0.09
    æĢ§å¼º
    -0.09
    åIJģ
    -0.09
    omers
    -0.09
    åĵº
    -0.09
    æ°´åĩĨ
    -0.08
    san
    -0.08
    .yang
    -0.08
    POSITIVE LOGITS
    æ°Ķè´¨
    0.10
    æĪĸå¤ļ
    0.10
    è´¨åľ°
    0.09
    kehr
    0.09
    红楼
    0.09
    æ¨Ĺ
    0.09
    祺
    0.09
    åıĬæŶ
    0.08
    thon
    0.08
    çĶŁäºİ
    0.08
    Activations Density 0.004%

    No Known Activations