© 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. 22232
    Prev
    Next
    INDEX
    Explanations

    electromyographic electrical activity and stimulation

    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
    éģĵæķĻ
    -0.08
    çĵ¦
    -0.08
     exercÃŃcio
    -0.08
     hosts
    -0.08
    violent
    -0.08
    顯
    -0.08
    OrUpdate
    -0.07
    å¼Ĥ
    -0.07
    ERE
    -0.07
    lore
    -0.07
    POSITIVE LOGITS
    æŃ¥æŃ¥
    0.10
    éħįä¸Ĭ
    0.10
    çĤ³
    0.10
    çİĭåħĪçĶŁ
    0.09
    èĬĻèĵī
    0.09
    ilig
    0.09
    åĪĨ红
    0.09
    æĪķ
    0.09
    丢失
    0.09
    dition
    0.09
    Activations Density 0.043%

    No Known Activations