© 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. 36893
    Prev
    Next
    INDEX
    Explanations

    last year

    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
    åĦ¿
    -0.10
    äºĨåIJĹ
    -0.10
    ENER
    -0.10
    æľ¬ç½ij
    -0.09
    edBy
    -0.09
    ilian
    -0.09
    ï¸
    -0.09
    åIJĦæł·
    -0.09
    orgh
    -0.09
    flo
    -0.09
    POSITIVE LOGITS
    vero
    0.09
    iero
    0.09
    ä¹ĭæīĢ
    0.09
    ç«Ļ
    0.08
    obs
    0.08
    æĪijä»¬ä¹Ł
    0.08
    ánd
    0.08
    -time
    0.08
    /frontend
    0.07
     nieu
    0.07
    Activations Density 0.011%

    No Known Activations