© 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. 37505
    Prev
    Next
    INDEX
    Explanations

    bill that expands legislation

    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
    ãģĦãģĨ
    -0.13
    ymm
    -0.10
    eer
    -0.10
    çĹĩ
    -0.10
    edian
    -0.10
    æĻŀ
    -0.10
    ettle
    -0.09
    edic
    -0.09
    CTION
    -0.09
    ../../../
    -0.09
    POSITIVE LOGITS
    iard
    0.14
    iards
    0.12
    ings
    0.11
    owing
    0.10
    mates
    0.10
    пÑĢакÑĤик
    0.09
    ender
    0.09
    inals
    0.09
    sworth
    0.09
    istic
    0.09
    Activations Density 0.014%

    No Known Activations