© 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. 63421
    Prev
    Next
    INDEX
    Explanations

    dividing into halves or parts

    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
    äºĨ好åĩł
    -0.11
    æľĢå°ij
    -0.10
    è¿Ļåĩłä¸ª
    -0.10
    alto
    -0.09
    äºĨåĩł
    -0.09
    ç¯Ģ
    -0.09
    åѤç«ĭ
    -0.09
    Inv
    -0.09
    è¿Ļåĩł
    -0.09
     Inv
    -0.08
    POSITIVE LOGITS
    åı¦ä¸ĢåįĬ
    0.28
    ä¸ĢåįĬ
    0.21
     halves
    0.17
     portion
    0.16
     половин
    0.15
    ä¸Ģéĥ¨åĪĨ
    0.15
    ä¸ĭåįĬ
    0.15
     part
    0.15
    -half
    0.15
    éĥ¨åĪĨ
    0.15
    Activations Density 0.163%

    No Known Activations