© 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. 52862
    Prev
    Next
    INDEX
    Explanations

    handling and performance characteristics

    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
    çŀł
    -0.09
    èĻ¹
    -0.09
    é¢Ĩ
    -0.09
    é¾ĻéŨ
    -0.09
    éłĺ
    -0.09
    gne
    -0.08
    udem
    -0.08
    تÙĪ
    -0.08
    าย
    -0.08
     Pret
    -0.08
    POSITIVE LOGITS
    稳å®ļæĢ§
    0.12
    çļĦæĦŁè§ī
    0.12
    ippy
    0.11
    æĢ§èĥ½
    0.11
    平稳
    0.11
     ëĬIJëĤĮ
    0.10
    æĦŁè§ī
    0.10
    çī¹æĢ§
    0.10
    åıįå¼¹
    0.09
     handling
    0.09
    Activations Density 0.065%

    No Known Activations