© 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. 53352
    Prev
    Next
    INDEX
    Explanations

    age and deficit

    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
    unate
    -0.11
    odyn
    -0.09
    loom
    -0.09
     вообÑīе
    -0.09
    -preview
    -0.09
    ensburg
    -0.09
    æĭĨ
    -0.08
     sứ
    -0.08
     Alo
    -0.08
    ãģİ
    -0.08
    POSITIVE LOGITS
    iens
    0.08
    çĪ¶åŃIJ
    0.08
    t
    0.08
    æĭ£
    0.08
    çħ¨
    0.08
    å¿¿
    0.08
    çĪ¸çĪ¸
    0.08
     slim
    0.08
     Otto
    0.08
    ãĤĦãģĻãģı
    0.08
    Activations Density 0.002%

    No Known Activations