© 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. 52214
    Prev
    Next
    INDEX
    Explanations

    family members and names

    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
    archy
    -0.09
    çĭİ
    -0.09
    åħ¬åŃIJ
    -0.09
    æģ£
    -0.09
    宾é¦Ĩ
    -0.09
    èĬ
    -0.08
    åı£å¾Ħ
    -0.08
     bada
    -0.08
    æŀī
    -0.08
    åĪĿæģĭ
    -0.08
    POSITIVE LOGITS
    好人
    0.10
    家åºŃ
    0.10
     family
    0.09
    æŃ¤æ¬¡
    0.09
    足迹
    0.09
    家æĹı
    0.09
    亲å±ŀ
    0.09
     Raider
    0.09
    family
    0.09
    家å±ŀ
    0.09
    Activations Density 0.033%

    No Known Activations