© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 7925
    Prev
    Next
    INDEX
    Explanations

    gear artifacts, gears, gear components

    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¸Ģçľ¼
    -0.09
    esthes
    -0.09
     createStore
    -0.09
    _filled
    -0.09
    vic
    -0.09
     Wall
    -0.09
    é¢ľ
    -0.09
    å°ıåºĹ
    -0.09
    filled
    -0.08
    enton
    -0.08
    POSITIVE LOGITS
     gears
    0.11
    ä¼łåĬ¨
    0.11
    лоÑĤ
    0.10
    齿轮
    0.10
    齿
    0.09
    è¾Ļ
    0.09
    é½Ĵ
    0.09
    è¾°
    0.09
    æ±Ĭ
    0.09
    åĪĩ
    0.09
    Activations Density 0.123%

    No Known Activations