© 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. 37101
    Prev
    Next
    INDEX
    Explanations

    nested structures or sequences

    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
    亲åĪĩ
    -0.10
    å°±æĺ¯è¿Ļæł·
    -0.10
    ç¹ĩ
    -0.09
    éŃĦ
    -0.09
    ä¹į
    -0.09
    éħį
    -0.09
    WER
    -0.09
    è¿ĻçĤ¹
    -0.09
    ãģ¨ãģĹãģ¦ãģ¯
    -0.08
    ETO
    -0.08
    POSITIVE LOGITS
    è¿ĽèĢĮ
    0.15
    åĨįåĪ°
    0.14
    åıĪæĺ¯
    0.14
    è¿Ľä¸ĢæŃ¥
    0.12
    ãģķãĤīãģ«
    0.12
    åıĪ被
    0.12
     nữa
    0.11
     further
    0.11
    åıĪ
    0.10
    çŃīä¸Ģç³»åĪĹ
    0.10
    Activations Density 0.274%

    No Known Activations