© 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. 9229
    Prev
    Next
    INDEX
    Explanations

    oral hygiene and teeth brushing habit

    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
    воз
    -0.10
    è·¨
    -0.10
    ä¸įèĪį
    -0.09
    çĩ¥
    -0.09
    ä¸ĭæĿ¥
    -0.08
    ç¬Ķè®°æľ¬
    -0.08
    storm
    -0.08
    _GPS
    -0.08
    çĵ¶é¢Ī
    -0.08
    edy
    -0.08
    POSITIVE LOGITS
    çīĻ
    0.12
    çīĻ齿
    0.11
     teeth
    0.10
    é¾ĭ
    0.10
    åĪ·
    0.09
    æ´ģ
    0.09
    èIJģ
    0.09
     Brushes
    0.09
     Ñģв
    0.09
    åłij
    0.09
    Activations Density 0.144%

    No Known Activations