© 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. 21403
    Prev
    Next
    INDEX
    Explanations

    sides of surfaces

    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
    åı¦ä¸ĢåįĬ
    -0.10
    人身
    -0.10
    èݪ
    -0.10
    ä¸ĢåĽ¢
    -0.09
     Bam
    -0.09
    åįĬå²Ľ
    -0.09
    奥æŀĹ
    -0.09
    主è§Ĥ
    -0.09
     Greenwood
    -0.09
    沿
    -0.09
    POSITIVE LOGITS
    POR
    0.09
    mil
    0.08
    å¡ij
    0.08
    ãģĵãģĨ
    0.08
     Coron
    0.08
    zar
    0.08
     mil
    0.08
     Mil
    0.08
     Robbie
    0.08
    âľħ
    0.08
    Activations Density 0.044%

    No Known Activations