© 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. 36622
    Prev
    Next
    INDEX
    Explanations

    livestock, sheep, cattle, movements

    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
    éĺ´éĺ³
    -0.11
    habit
    -0.11
    æľĽ
    -0.10
     Habit
    -0.10
    æī«
    -0.09
    èī®
    -0.09
    cki
    -0.09
     habit
    -0.09
     chem
    -0.09
     ÐľÐ°Ðº
    -0.09
    POSITIVE LOGITS
    çī²
    0.12
     Sheep
    0.11
    ç¾Ĭ
    0.10
    çī§åľº
    0.10
    çī§
    0.10
     sheep
    0.10
    ä¸Ģ头
    0.10
    çķľçī§ä¸ļ
    0.10
     livestock
    0.10
    åŀĽ
    0.10
    Activations Density 0.059%

    No Known Activations