© 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. 7263
    Prev
    Next
    INDEX
    Explanations

    have a look

    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
    æľīæĿ¡ä»¶
    -0.10
    icut
    -0.09
    亡
    -0.09
    ourd
    -0.09
    åĨī
    -0.09
    å¦ŀ
    -0.09
    踵
    -0.09
    ä¾ĿçĦ¶
    -0.09
    丰满
    -0.08
    æ°´åĩĨ
    -0.08
    POSITIVE LOGITS
    çľĭä¸Ģä¸ĭ
    0.12
    è¯ķè¯ķ
    0.10
    èģĬ
    0.10
    çľĭæĿ¥
    0.10
    lore
    0.10
    éĴ»çłĶ
    0.09
    æĮ¥
    0.09
    wit
    0.09
    çľĭçľĭ
    0.09
    yro
    0.09
    Activations Density 0.041%

    No Known Activations