© 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. 34562
    Prev
    Next
    INDEX
    Explanations

    proper names and specific terms

    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
    utoff
    -0.10
    Ñĩик
    -0.10
     spo
    -0.09
    çİĭçīĮ
    -0.09
    çķĮçļĦ
    -0.09
    æ²ģ
    -0.09
    第äºĮç§į
    -0.09
    æľ½
    -0.09
    atura
    -0.09
    yte
    -0.08
    POSITIVE LOGITS
    ides
    0.10
    andra
    0.10
    usz
    0.09
    CPP
    0.08
    ä¹ĭæĹħ
    0.08
    åīįåı°
    0.08
    raph
    0.08
    ä¼Ĺ
    0.08
    -es
    0.08
    LI
    0.08
    Activations Density 0.006%

    No Known Activations