© 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. 20886
    Prev
    Next
    INDEX
    Explanations

    Cumberland Valley Regional Division

    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
    å¤ļåįĬ
    -0.10
    åĩĢåĮĸ
    -0.09
    侮辱
    -0.09
    atar
    -0.09
    çĶļèĩ³æĺ¯
    -0.09
     Loch
    -0.09
    iali
    -0.09
    åİĨåı²æĸ°
    -0.08
    åIJĦ项
    -0.08
    ukes
    -0.08
    POSITIVE LOGITS
    åĢĻ
    0.09
    æĦıè¯Ĩ
    0.09
    _CY
    0.09
    CMS
    0.08
     еÑģÑĤÑĮ
    0.08
     Reb
    0.08
     consciousness
    0.08
    uja
    0.08
    æ²Ļ
    0.08
    çľĭä¸įè§ģ
    0.08
    Activations Density 0.006%

    No Known Activations