© 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. 51427
    Prev
    Next
    INDEX
    Explanations

    aquacel, aquarist, aquaman

    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
     rep
    -0.09
    rep
    -0.09
    ponge
    -0.09
    代
    -0.09
    åIJ¬åıĸ
    -0.09
    Spoiler
    -0.09
    åī¥
    -0.09
    åħ´æĹº
    -0.09
     Hoy
    -0.09
     Sponge
    -0.09
    POSITIVE LOGITS
    å¸ı
    0.10
    æİ£
    0.09
    Disposable
    0.09
    çĶŁäº§åĴĮ
    0.09
     çeÅŁ
    0.09
    帷
    0.08
    çĥŃæ°´åĻ¨
    0.08
    çıłæ±Ł
    0.08
    仪
    0.08
    urate
    0.08
    Activations Density 0.052%

    No Known Activations