© 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. 37760
    Prev
    Next
    INDEX
    Explanations

    pop culture and music

    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
    auc
    -0.09
    umeric
    -0.09
     Kick
    -0.08
    宾客
    -0.08
    éĴ¢
    -0.08
    主æĮģ人
    -0.08
    aan
    -0.08
    bere
    -0.08
    æīĢå¾Ĺ
    -0.08
    æĭĹ
    -0.08
    POSITIVE LOGITS
    /pop
    0.10
    pop
    0.09
    اذ
    0.08
    çİĭåŃIJ
    0.08
     Wyn
    0.08
    åĵĨ
    0.08
    eton
    0.08
    çľ¼æ³ª
    0.08
    (pop
    0.08
    /popper
    0.08
    Activations Density 0.027%

    No Known Activations