© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38316
    Prev
    Next
    INDEX
    Explanations

    image or video file names

    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
    .crt
    -0.09
    éģĵçIJĨ
    -0.09
    åIJĦçľģ
    -0.09
    ä¸įåĨį
    -0.08
    å¨ĺ
    -0.08
    éľĢè¦ģçĶ¨
    -0.08
    æİĺ
    -0.08
    kes
    -0.08
    vant
    -0.08
    好ä¸į好
    -0.08
    POSITIVE LOGITS
    annie
    0.10
    ogi
    0.10
    è®Ń
    0.09
    è¾Ĥ
    0.09
    夸
    0.08
    é¢IJ
    0.08
     Macron
    0.08
    çĽİ
    0.08
    æĶ¾åĩº
    0.08
    ehr
    0.08
    Activations Density 0.004%

    No Known Activations