© 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. 62858
    Prev
    Next
    INDEX
    Explanations

    tax-exempt donations and savings accounts

    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
    ä½ĵè´´
    -0.09
    塾
    -0.09
    /rem
    -0.09
    prt
    -0.09
    æĪı
    -0.09
    ä¸ĭåįĬ
    -0.09
    åıĺçİ°
    -0.09
    éĵIJ
    -0.09
    èIJ
    -0.09
    reck
    -0.09
    POSITIVE LOGITS
    裴
    0.08
    禾
    0.08
     Hughes
    0.08
    ä¸Ģçľ¼
    0.08
    ingu
    0.08
     å¿
    0.08
    eh
    0.08
    uro
    0.08
    å®ĹæŨ
    0.08
    imb
    0.07
    Activations Density 0.009%

    No Known Activations