© 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. 38159
    Prev
    Next
    INDEX
    Explanations

    house music genres

    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
    åĬĽåѦ
    -0.11
    èĤ¡æľ¬
    -0.09
    ä¸Ģåī¯
    -0.09
    hipster
    -0.09
    åıĤ
    -0.09
    人身
    -0.09
    iban
    -0.08
     ì°¸
    -0.08
     Cunning
    -0.08
    æŀķ头
    -0.08
    POSITIVE LOGITS
     Stam
    0.09
    ames
    0.09
    éĺĶ
    0.08
    殿
    0.08
    èIJ¥
    0.08
    ãĥĥãĤ·
    0.08
    ollower
    0.08
    éķľåŃIJ
    0.08
    ATAB
    0.08
    ож
    0.08
    Activations Density 0.043%

    No Known Activations