© 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. 30723
    Prev
    Next
    INDEX
    Explanations

    color description

    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
    纵深
    -0.10
     Cooler
    -0.10
    åıĭåĸĦ
    -0.09
    çľģåĨħ
    -0.09
    ÑģÑĤа
    -0.09
    éĻį
    -0.09
    åĭ¤åĬ³
    -0.09
    å®īä¿Ŀ
    -0.09
    illator
    -0.09
     Bain
    -0.09
    POSITIVE LOGITS
    为æŃ¢
    0.14
    æĦŁè§ī
    0.12
    ä¸įåĨįæĺ¯
    0.10
    çľĭä¸įåĩº
    0.10
    æĦŁè¦º
    0.10
    æĺİæĺ¾
    0.10
    è¿Ļæīįæĺ¯
    0.10
    ä¸įåĨį
    0.09
    çļĦæĦŁè§ī
    0.09
    éĿ¢èī²
    0.09
    Activations Density 0.063%

    No Known Activations