© 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. 30686
    Prev
    Next
    INDEX
    Explanations

    new orleans saints

    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
    rics
    -0.10
    æĪij们ä¸Ģèµ·
    -0.10
    çļĦ妻åŃIJ
    -0.10
    峦
    -0.10
    äºĨ大éĩıçļĦ
    -0.09
     vợ
    -0.09
    fully
    -0.09
    æºľ
    -0.08
    碣
    -0.08
    ãĥ¼ãĤ¸
    -0.08
    POSITIVE LOGITS
    liness
    0.09
    obil
    0.09
    ense
    0.09
    /editor
    0.08
    ENSE
    0.08
    说æĺ¯
    0.08
    -ending
    0.08
    éĤ¦
    0.08
    clar
    0.08
    ç¬Ļ
    0.08
    Activations Density 0.002%

    No Known Activations