© 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. 36982
    Prev
    Next
    INDEX
    Explanations

    biopsy/sampling

    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
    å¾ĹåĪĨ
    -0.10
    uja
    -0.10
    INU
    -0.10
    æ¸ħç®Ĺ
    -0.09
     Shoe
    -0.09
    :;"
    -0.09
    è§Ĵèī²
    -0.09
    âĺ¢
    -0.09
    åIJij举
    -0.09
    ìĸ¼
    -0.09
    POSITIVE LOGITS
     samples
    0.17
    æł·åĵģ
    0.16
    æł·æľ¬
    0.16
     sample
    0.14
    éĩĩ
    0.14
     sampling
    0.13
    éĩĩéĽĨ
    0.13
     Samples
    0.13
    samples
    0.13
    .sample
    0.12
    Activations Density 0.197%

    No Known Activations