© 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. 37085
    Prev
    Next
    INDEX
    Explanations

    position

    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
    伸
    -0.10
    åĴĮå¹³
    -0.10
    ä¸įäºĪ
    -0.09
     pier
    -0.09
    ç©¿éĢı
    -0.08
    ãĥŃãĥ¼
    -0.08
    itant
    -0.08
    -driving
    -0.08
    æĭĦ
    -0.08
     Municipal
    -0.08
    POSITIVE LOGITS
    åĪ°ä½į
    0.15
    姿åĬ¿
    0.12
     ready
    0.12
    ä½įç½®
    0.12
     position
    0.12
     Position
    0.12
     positions
    0.11
    -position
    0.11
    ready
    0.11
    Position
    0.11
    Activations Density 0.038%

    No Known Activations