© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20864
    Prev
    Next
    INDEX
    Explanations

    past tense verbs, "to be" variations

    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
    éģĺ
    -0.10
    æĥ©ç½ļ
    -0.10
     Ñģобой
    -0.09
    æĮ½æķij
    -0.09
    ospel
    -0.09
    astr
    -0.09
    UFF
    -0.09
    çĸ´
    -0.08
    çŃĶé¢ĺ
    -0.08
    æīįåıijçİ°
    -0.08
    POSITIVE LOGITS
    ä½ľä¸º
    0.11
    æĭħä»»
    0.11
    åħ¶éĹ´
    0.11
    ä½ľçĤº
    0.09
    amas
    0.09
    é»İ
    0.09
    ç»Ī身
    0.09
    kl
    0.08
    ora
    0.08
    ç»ĪçĶŁ
    0.08
    Activations Density 0.138%

    No Known Activations