© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 56639
    Prev
    Next
    INDEX
    Explanations

    DJs and music producers

    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
    antan
    -0.10
    çİ®
    -0.09
    å¸ĺ
    -0.08
    .actor
    -0.08
    lan
    -0.08
    PTH
    -0.08
    è´¬
    -0.08
     ÙĪØ·ÙĨÙĬ
    -0.08
    LAN
    -0.08
    à¹Ģà¸Ħล
    -0.08
    POSITIVE LOGITS
    导å¸Ī
    0.10
     DJ
    0.09
    æĬĬæİ§
    0.09
    èijĹ
    0.09
     DJs
    0.09
    mania
    0.09
    ç´łæĿIJ
    0.09
    çĵ¶åŃIJ
    0.09
    ãģķãģĪ
    0.08
    大åİħ
    0.08
    Activations Density 0.099%

    No Known Activations