© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5313
    Prev
    Next
    INDEX
    Explanations

    alignment and optical

    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
    .localization
    -0.10
    eki
    -0.09
    asti
    -0.09
    贯穿
    -0.09
    è¿Ļ段
    -0.09
     Ranking
    -0.09
    ategorical
    -0.08
    åĿıäºĨ
    -0.08
    å·´æĭī
    -0.08
    åĬ¨èĦī
    -0.08
    POSITIVE LOGITS
    磫æŃ£
    0.11
    åģıå·®
    0.10
    çºłæŃ£
    0.10
    è§Ĵ度
    0.09
    åį°åĪ·
    0.09
     alignment
    0.09
    eus
    0.09
    дов
    0.09
    çļĦè§Ĵ度
    0.08
    å¾®å¦Ļ
    0.08
    Activations Density 0.227%

    No Known Activations