© 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. 52171
    Prev
    Next
    INDEX
    Explanations

    dental teeth

    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
    ä¿¡èµĸ
    -0.09
    èħ¹
    -0.09
    éħįæĸĻ
    -0.09
    转è¿IJ
    -0.09
    åįĩéĻį
    -0.09
    绳
    -0.09
    åĨĮ
    -0.09
    çŀĦ
    -0.09
    éĶij
    -0.09
    毯
    -0.09
    POSITIVE LOGITS
    çīĻ齿
    0.22
    çīĻ
    0.21
    齿
    0.18
     dental
    0.18
     teeth
    0.17
     tooth
    0.17
     Dental
    0.16
     зÑĥб
    0.16
     dentist
    0.16
    é½Ĵ
    0.15
    Activations Density 0.376%

    No Known Activations