© 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. 6908
    Prev
    Next
    INDEX
    Explanations

    Roman Catholic

    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
    çĦ¶
    -0.09
    对æĸ¹
    -0.09
     Gow
    -0.09
     Thom
    -0.08
    .year
    -0.08
    夤
    -0.08
    æŃ¤äºº
    -0.08
    æıĸ
    -0.08
    пÑĢеÑģÑģ
    -0.08
    åįĩ
    -0.08
    POSITIVE LOGITS
    åıijå±ķåīįæĻ¯
    0.10
    åĪĨæĶ¯
    0.10
    æĪı
    0.10
     trụ
    0.10
     ì¤ijìĭ¬
    0.09
    æģĻ
    0.09
     Roe
    0.09
    åĩºæ±Ĺ
    0.09
    æĢ»éĥ¨
    0.09
    åįļæĸĩ
    0.09
    Activations Density 0.077%

    No Known Activations