© 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. 58566
    Prev
    Next
    INDEX
    Explanations

    treatments administered or received

    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
    ä¹ĥèĩ³
    -0.11
    eut
    -0.10
    erre
    -0.10
    éģĹæĨ¾
    -0.10
     Circus
    -0.10
    å¾ĩ
    -0.09
    齿
    -0.09
    DCF
    -0.09
    .Suppress
    -0.09
    ROTO
    -0.09
    POSITIVE LOGITS
    è¦ģä¹Ī
    0.09
     either
    0.09
     randomized
    0.08
     harmless
    0.08
    ç»Ļä»ĸ们
    0.08
    ä½Ĩä»ĸ们
    0.08
    å½¼ãĤī
    0.08
    ä¸įéĢļ
    0.08
    ä»ĸ们çļĦ
    0.07
    çłĶ究ä¸Ńå¿ĥ
    0.07
    Activations Density 1.055%

    No Known Activations