© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6856
    Prev
    Next
    INDEX
    Explanations

    medical aid and services

    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
    人å±ħ
    -0.11
    ICLE
    -0.09
    ÑģÑĤи
    -0.09
    à¹Ģà¸Ħ
    -0.09
    örü
    -0.09
    åĬĽåѦ
    -0.08
    ä¹ĸä¹ĸ
    -0.08
    æĥ³äºĨ
    -0.08
    à¸ĩ
    -0.08
    Meal
    -0.08
    POSITIVE LOGITS
    æĢ¥æķij
    0.15
    åĮ»èį¯
    0.14
    åĮ»çĸĹ
    0.14
    è¯ĬæīĢ
    0.12
    æķijæĬ¤
    0.12
    æķijæ²»
    0.11
     Shadow
    0.11
    åĮ»çĸĹæľįåĬ¡
    0.10
    èį¯åĵģ
    0.10
    .shadow
    0.10
    Activations Density 0.051%

    No Known Activations