© 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. 30536
    Prev
    Next
    INDEX
    Explanations

    most recent

    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
    ishop
    -0.10
    èĤĨ
    -0.09
    à¹Ĩ
    -0.09
    æľĢçµĤ
    -0.09
    糯
    -0.09
    æľĢç»Ī
    -0.08
    å¼Ģçİ©ç¬ij
    -0.08
    roc
    -0.08
    cre
    -0.08
    级以ä¸Ĭ
    -0.08
    POSITIVE LOGITS
    ä¸Ģè½®
    0.10
    .backends
    0.09
    ä¸Ģæī¹
    0.09
    mare
    0.09
    èľĥ
    0.09
    /current
    0.08
    ä¸Ģ件äºĭæĥħ
    0.08
     Gaul
    0.08
    åĬłä¹ĭ
    0.08
    ãģĵãģ¨ãģ«
    0.08
    Activations Density 0.008%

    No Known Activations