© 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. 53241
    Prev
    Next
    INDEX
    Explanations

    medical equipment, imaging, items

    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
    å·½
    -0.10
    opup
    -0.10
    abelle
    -0.09
    าà¸ĩ
    -0.09
    ouver
    -0.09
     пÑĢоб
    -0.09
    ç¾İ丽乡æĿij
    -0.08
     nuis
    -0.08
    çŁŃçŁŃ
    -0.08
     Malik
    -0.08
    POSITIVE LOGITS
    åĮ»çĸĹ
    0.13
    åĮ»çĸĹæľįåĬ¡
    0.13
    medical
    0.13
    åĮ»
    0.12
     medical
    0.12
    åĮ»èį¯
    0.12
    åĮ»çĸĹåį«çĶŁ
    0.11
    ðŁı¥
    0.11
    çĶ¨èį¯
    0.11
    çľĭçĹħ
    0.11
    Activations Density 0.258%

    No Known Activations