© 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. 10586
    Prev
    Next
    INDEX
    Explanations

    .S. followed by period

    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
    壮大
    -0.09
     Perkins
    -0.09
    ç«ŀä»·
    -0.08
    äºļè¿IJä¼ļ
    -0.08
    è§ģ解
    -0.08
    åħĥå®Ŀ
    -0.08
    åĽłåŃIJ
    -0.08
    家å±ŀ
    -0.08
    åĪĩéĻ¤
    -0.08
    æºĸ
    -0.08
    POSITIVE LOGITS
    佬
    0.09
    龸
    0.09
    å¹ħ
    0.09
    /world
    0.09
    DialogTitle
    0.08
    quine
    0.08
    otta
    0.08
    碲
    0.08
    ТЬ
    0.08
     mé
    0.08
    Activations Density 0.039%

    No Known Activations