© 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. 51918
    Prev
    Next
    INDEX
    Explanations

    shotgun

    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
     Ñģамого
    -0.09
    ä¹İ
    -0.09
    ive
    -0.09
    åı¯æĥ³
    -0.09
    ury
    -0.09
    ä¸Ĭåİ»
    -0.08
    é£İå°ļ
    -0.08
     Trident
    -0.08
    ension
    -0.08
    CONDITION
    -0.08
    POSITIVE LOGITS
    ç¹ĩ
    0.10
    à¸Ńร
    0.10
    alties
    0.09
    ا
    0.09
    峡
    0.09
    iens
    0.09
    åIJ
    0.09
     kms
    0.09
    ãģĮãĤī
    0.08
    çĦ¶æĺ¯
    0.08
    Activations Density 0.002%

    No Known Activations