© 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. 54120
    Prev
    Next
    INDEX
    Explanations

    table formatting characters

    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
    isoft
    -0.09
    ằ
    -0.09
    æ¹ĥ
    -0.08
    妹
    -0.08
    翻身
    -0.08
    å¸Ńåį·
    -0.08
    arden
    -0.08
    icus
    -0.08
    è¿Ī
    -0.08
     ÑĢеб
    -0.08
    POSITIVE LOGITS
    FTA
    0.09
    sam
    0.09
    ä¸Ģä½ĵ
    0.09
     Ñģам
    0.08
    åIJ¸
    0.08
    urst
    0.08
    Ìģ
    0.08
    ä¸ĭ次
    0.08
    ä¸Ģç«Ļ
    0.08
    æĥħ人
    0.08
    Activations Density 0.110%

    No Known Activations