© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8427
    Prev
    Next
    INDEX
    Explanations

    born or borne

    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
    æѦè£ħ
    -0.12
    domain
    -0.10
    rial
    -0.09
    çİ°è¡Į
    -0.09
    mos
    -0.09
    dar
    -0.09
    tes
    -0.09
    بÙĪت
    -0.09
    éģĵ士
    -0.08
    itel
    -0.08
    POSITIVE LOGITS
     resemblance
    0.10
    åħ³åĪĩ
    0.10
    æĭħ
    0.09
    beiten
    0.09
    wend
    0.09
    æ¡Ĥ
    0.09
     witness
    0.09
     Walsh
    0.09
    bearing
    0.09
    訾
    0.08
    Activations Density 0.040%

    No Known Activations