© 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. 9015
    Prev
    Next
    INDEX
    Explanations

    on this page

    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
     اÙĦØŃصÙĪÙĦ
    -0.11
    OnClick
    -0.11
    ฯ
    -0.11
    åİ»åĮ»éĻ¢
    -0.10
    æľīå¤ļå°ij
    -0.10
     onsite
    -0.10
    æľīå¿ħè¦ģ
    -0.10
    /qu
    -0.10
    åīį身
    -0.10
    ÑĤаÑĢ
    -0.10
    POSITIVE LOGITS
     behalf
    0.28
    /off
    0.21
    shore
    0.17
    -going
    0.15
    -site
    0.14
    /about
    0.14
    -line
    0.14
     occasion
    0.13
    boarding
    0.13
    /from
    0.13
    Activations Density 0.521%

    No Known Activations