© 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. 53533
    Prev
    Next
    INDEX
    Explanations

    gaming and esports

    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
    èĬŃ
    -0.09
    éĶ·
    -0.09
    å¤©åľ°
    -0.08
     Politico
    -0.08
    海滩
    -0.08
     Ð
    -0.08
    绶
    -0.08
    å§Ĭ妹
    -0.08
    æī¿æİ¥
    -0.08
    çĿ
    -0.08
    POSITIVE LOGITS
    è±Ĩ
    0.09
    太é«ĺ
    0.09
    lob
    0.09
     Flux
    0.09
     Fen
    0.09
     Dota
    0.09
    åĿij
    0.08
    flux
    0.08
    èĥĮ
    0.08
    LAG
    0.08
    Activations Density 0.081%

    No Known Activations