© 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. 20056
    Prev
    Next
    INDEX
    Explanations

    past tense verbs followed by event details

    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
    å±ħçĦ¶
    -0.10
    çĶŁæĢķ
    -0.08
    ведиÑĤе
    -0.08
    ENDOR
    -0.08
    åģıåģı
    -0.08
    iesz
    -0.08
    åıįèĢĮ
    -0.08
    ç«ŁçĦ¶
    -0.08
    æĪijå¦Ī
    -0.08
    ç«Ł
    -0.08
    POSITIVE LOGITS
    ä¸Ģ缴éĥ½æĺ¯
    0.12
    æѤåīį
    0.11
    ä¸Ģ缴æĺ¯
    0.11
    æį®æĤī
    0.11
    åħĪåīį
    0.10
    å·²ç»ıæľī
    0.10
    缮åīį为æŃ¢
    0.10
    æī«
    0.10
    å·²ç»ıæĺ¯
    0.09
    éĥ½å·²ç»ı
    0.09
    Activations Density 0.284%

    No Known Activations