© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 7795
    Prev
    Next
    INDEX
    Explanations

    livestock and livelihood

    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
    åĮ»åѦéĻ¢
    -0.10
    ific
    -0.09
    abis
    -0.09
    ìĹ´
    -0.09
    ORT
    -0.09
     знаÑĩиÑĤ
    -0.09
    OOT
    -0.09
    uchi
    -0.08
    halb
    -0.08
    馥
    -0.08
    POSITIVE LOGITS
    åİ¥
    0.11
    sWith
    0.10
    稷
    0.10
    ä¹ĭä½ľ
    0.09
    eper
    0.09
     Lud
    0.09
    ester
    0.08
    inals
    0.08
    iad
    0.08
    麽
    0.08
    Activations Density 0.008%

    No Known Activations