© 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. 56748
    Prev
    Next
    INDEX
    Explanations

    Mexican wave

    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
    OURS
    -0.11
    uzu
    -0.09
    INGTON
    -0.09
    -hole
    -0.09
    UGE
    -0.09
    æŃ¥åħ¥
    -0.09
    审è§Ĩ
    -0.09
    çŀ©çĽ®
    -0.09
    iba
    -0.09
    ç»Ĩç»Ĩ
    -0.09
    POSITIVE LOGITS
    bare
    0.09
    è¶ģ
    0.08
    OfClass
    0.08
     Cla
    0.08
    åģ¥
    0.08
    orig
    0.08
    hip
    0.08
    à¹Ģà¸ĸ
    0.08
    .tap
    0.08
    ough
    0.08
    Activations Density 0.006%

    No Known Activations