© 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. 20507
    Prev
    Next
    INDEX
    Explanations

    dental smiles

    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
     paraph
    -0.11
    à¸łà¸²
    -0.09
    èľļ
    -0.08
    CBC
    -0.08
    é¥ķ
    -0.08
    -dev
    -0.08
    ãĤĩ
    -0.08
     kiá»ĩn
    -0.08
    mic
    -0.08
    èĢĦ
    -0.08
    POSITIVE LOGITS
    å¾®ç¬ij
    0.25
    ç¬ij容
    0.23
     smile
    0.23
    çļĦç¬ij容
    0.22
    ç¬ijèĦ¸
    0.22
    ä¸Ģç¬ij
    0.22
     smiles
    0.21
    ç¬ijäºĨ
    0.19
     smiled
    0.19
     Smile
    0.18
    Activations Density 0.038%

    No Known Activations