© 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. 7820
    Prev
    Next
    INDEX
    Explanations

    tooltip and title attributes

    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
    宾客
    -0.10
    è°Īè°Ī
    -0.09
    éĵ·
    -0.09
    ayout
    -0.09
    orsi
    -0.09
    èµ
    -0.09
    opy
    -0.08
    à¹ģยà¸ģ
    -0.08
    å°ıæľĭåıĭ
    -0.08
    intosh
    -0.08
    POSITIVE LOGITS
    åı®
    0.09
    ÑĩÑĮ
    0.09
    lops
    0.09
     Werk
    0.09
     Ñģобой
    0.09
    å¿Ļ
    0.09
    оÑģÑĤи
    0.09
    æĪIJéķ¿ä¸º
    0.09
    åĪ°å¤Ħ
    0.08
    çĽ²
    0.08
    Activations Density 0.096%

    No Known Activations