© 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. 23470
    Prev
    Next
    INDEX
    Explanations

    highest ranking and population statistics

    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
     обÑĥÑĩ
    -0.09
    ilio
    -0.08
    æľŁéĻIJ
    -0.08
    ļ
    -0.08
    ød
    -0.08
    æĦıåIJij
    -0.08
     оÑĢи
    -0.08
     Ramadan
    -0.08
    æĸ°åĨľæĿij
    -0.08
    icom
    -0.08
    POSITIVE LOGITS
    ä¸İåħ¶ä»ĸ
    0.12
    ä»ħ次äºİ
    0.12
    åĴĮåħ¶ä»ĸ
    0.11
    åIJįåĪĹåīįèĮħ
    0.10
    é¦ĸåĪĽ
    0.10
    åIJįåĪĹ
    0.10
    æİĴåIJį
    0.10
    æ¯Ķè¾ĥé«ĺ
    0.10
     among
    0.10
    æľĢé«ĺçļĦ
    0.10
    Activations Density 0.102%

    No Known Activations