© 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. 9184
    Prev
    Next
    INDEX
    Explanations

    Rh-related words

    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
    íŀĪ
    -0.10
    BarItem
    -0.09
    çIJ
    -0.09
    ãĤ¦ãĥ³
    -0.09
    ment
    -0.09
     tá»ĩ
    -0.09
     cú
    -0.08
    汪
    -0.08
    ä¼Ļ
    -0.08
    ador
    -0.08
    POSITIVE LOGITS
    orical
    0.11
    å¼Ń
    0.10
    é©·
    0.09
    /or
    0.09
    ets
    0.09
    ynch
    0.09
    osoph
    0.08
    éªĸ
    0.08
    æĶ»åħ³
    0.08
    åĦ¿å¥³
    0.08
    Activations Density 0.064%

    No Known Activations