© 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. 4541
    Prev
    Next
    INDEX
    Explanations

    list items or categories

    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
    isi
    -0.08
    iana
    -0.08
    elay
    -0.08
    容纳
    -0.08
    æłĩåĩĨåĮĸ
    -0.08
    强æľīåĬĽçļĦ
    -0.08
    egan
    -0.08
    eters
    -0.08
    Ĵ
    -0.07
    åĩĢèµĦ产
    -0.07
    POSITIVE LOGITS
    åĪļæīį
    0.09
    æŁ¥çľĭåħ¨æĸĩ
    0.09
    igner
    0.08
    irit
    0.08
    ä»ħ代表
    0.08
    ä¹ĭ声
    0.08
    çī¹åĪ«å£°æĺİ
    0.08
     пÑĢедлаг
    0.08
    è¿Ļ个è¯į
    0.08
     дома
    0.08
    Activations Density 0.749%

    No Known Activations