© 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. 58173
    Prev
    Next
    INDEX
    Explanations

    church splits and branches

    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
    çĮ®
    -0.09
    asso
    -0.09
    ä¸ĢæĿ¡
    -0.09
    æĶ¾è¿Ľ
    -0.08
    绶
    -0.08
    ä¸Ģé¦ĸ
    -0.08
    æĹ¢æĺ¯
    -0.08
     casc
    -0.08
    ä¸į论
    -0.08
     chap
    -0.08
    POSITIVE LOGITS
    è£Ĥ
    0.14
    åĪĨè£Ĥ
    0.14
    æĥĭ
    0.11
     splits
    0.10
    èģ²
    0.10
    æ¨Ĺ
    0.10
    åĥµ
    0.10
    /Branch
    0.10
    åĪĨæĶ¯
    0.10
    çļĦçĶ»éĿ¢
    0.09
    Activations Density 0.061%

    No Known Activations