© 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. 49054
    Prev
    Next
    INDEX
    Explanations

    resounding, unanimously, forcefully, adamant, flat-out

    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
    Translations
    -0.09
    å¥ijæľº
    -0.08
    èѦæĥķ
    -0.08
    haps
    -0.08
    ombok
    -0.08
     ìĺ¤íŀĪ볤
    -0.08
     DVR
    -0.08
     crest
    -0.08
    à¸Ńาย
    -0.08
    åŃĺæĶ¾
    -0.08
    POSITIVE LOGITS
    beat
    0.10
    sWith
    0.10
    æŬ
    0.09
    太平
    0.09
    ãģĹãĤĥ
    0.09
    åıį对
    0.09
    cakes
    0.09
     beat
    0.09
    yle
    0.08
    åĿ³
    0.08
    Activations Density 0.014%

    No Known Activations