© 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. 32664
    Prev
    Next
    INDEX
    Explanations

    County, area, district, shire

    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
    æºIJæºIJä¸įæĸŃ
    -0.10
    æģ»
    -0.10
    æłij
    -0.10
     forest
    -0.10
    lover
    -0.10
    tree
    -0.10
    森æŀĹ
    -0.09
     tree
    -0.09
    .tp
    -0.09
     Beng
    -0.09
    POSITIVE LOGITS
    æ²Ļæ¼ł
    0.13
     Desert
    0.10
    æ²Ļ
    0.09
     desert
    0.09
    çłĤ
    0.09
    å¹²çĩ¥
    0.09
     Sahara
    0.09
    бÑĢ
    0.09
    翼
    0.09
     TAS
    0.09
    Activations Density 0.192%

    No Known Activations