© 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. 33631
    Prev
    Next
    INDEX
    Explanations

    centralized and decentralized

    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
    ılı
    -0.09
    зав
    -0.09
    人为
    -0.09
    æĥĬ
    -0.08
    å±Ĥå±Ĥ
    -0.08
    éĢIJ
    -0.08
    riculum
    -0.08
    صÙĪÙĦ
    -0.08
    argo
    -0.08
    ythe
    -0.08
    POSITIVE LOGITS
    eker
    0.09
    对åħ¬åı¸
    0.09
    驽
    0.09
    訾
    0.09
    edly
    0.09
    леÑĢ
    0.08
    errer
    0.08
    åį°
    0.08
    eee
    0.08
    åįĥéĩĮ
    0.08
    Activations Density 0.007%

    No Known Activations