© 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. 53189
    Prev
    Next
    INDEX
    Explanations

    Vita TV, :], Shelton, Stapleton

    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
    å¼Ģåı£
    -0.11
    åIJĮæł·çļĦ
    -0.09
    .rf
    -0.09
    ä»ĸæĽ¾
    -0.09
    _ENTER
    -0.09
     завод
    -0.09
    .dk
    -0.09
    ãģªãģĦãģĵãģ¨
    -0.09
    çķ´
    -0.09
    .oracle
    -0.09
    POSITIVE LOGITS
    неж
    0.10
    7
    0.09
    6
    0.09
    1
    0.09
     Schön
    0.08
    5
    0.08
     Kend
    0.08
    8
    0.08
    zan
    0.08
    iÄį
    0.08
    Activations Density 0.003%

    No Known Activations