© 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. 3510
    Prev
    Next
    INDEX
    Explanations

    thought the assumption

    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
    CellValue
    -0.09
     Gandhi
    -0.09
    é¢ł
    -0.09
    å©Ĩ
    -0.09
    ë°Ķ
    -0.09
    åį¦
    -0.09
    復
    -0.08
    åı¯ä»¥çľĭåĪ°
    -0.08
    å¿ħä¸įåı¯
    -0.08
    åķ¬
    -0.08
    POSITIVE LOGITS
    è¿ĺ以为
    0.17
    以为
    0.14
    ãģ¨æĢĿãģ£ãģ¦ãģĦãģŁ
    0.12
    åıªçŁ¥éģĵ
    0.12
    以çĤº
    0.11
    æĪij以为
    0.11
    åIJ¬è¯´è¿ĩ
    0.11
    вл
    0.11
    ä¸Ģ缴æĺ¯
    0.10
    çļĦåį°è±¡
    0.10
    Activations Density 0.096%

    No Known Activations