© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8004
    Prev
    Next
    INDEX
    Explanations

    degree or extent

    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
     Dai
    -0.10
     Kang
    -0.10
    ensation
    -0.09
    umer
    -0.09
    ENE
    -0.08
     feas
    -0.08
     unserialize
    -0.08
     Garner
    -0.08
    uitable
    -0.08
    UCE
    -0.08
    POSITIVE LOGITS
    ä¿¡æģ¯åħ¬å¼Ģ
    0.09
     ilk
    0.09
    æĭĴ
    0.09
     proven
    0.09
    æŀķ
    0.09
     concern
    0.08
    å®°
    0.08
    ÑĤиÑĢ
    0.08
    裹
    0.08
    åľ¨é¦Ļ港
    0.08
    Activations Density 0.137%

    No Known Activations