© 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. 11388
    Prev
    Next
    INDEX
    Explanations

    Heraklion; Rhodes; Dalmatia

    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
    æĹłç¼Ŀ
    -0.09
    ä¸Ģ头
    -0.09
    ä¸Ģåı£
    -0.09
    ä¾Ľåħ»
    -0.08
    ETCH
    -0.08
    æĢ»ä½ĵ
    -0.08
    æ²³æµģåŁŁ
    -0.08
     Shuffle
    -0.08
    åįľ
    -0.08
    ä½ķ
    -0.08
    POSITIVE LOGITS
    æĭįæĭį
    0.09
    èѦæĸ¹
    0.09
    axed
    0.09
    erial
    0.09
     Baron
    0.08
     пом
    0.08
    éģĹ
    0.08
    ching
    0.08
    çĹħ
    0.08
     поÑĢÑĤал
    0.08
    Activations Density 0.014%

    No Known Activations