© 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. 37960
    Prev
    Next
    INDEX
    Explanations

    this followed by content type

    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
    éĥľ
    -0.09
    èµĬ
    -0.08
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.08
    orary
    -0.08
    çļĦåĦ¿åŃIJ
    -0.08
    åģļå·¥
    -0.08
    对ä»ĸ们
    -0.07
    obody
    -0.07
    äºĮ线
    -0.07
    å§ĭ建
    -0.07
    POSITIVE LOGITS
    mens
    0.09
     пÑĢÑı
    0.09
     Seah
    0.09
    .readValue
    0.09
    æĸŃ
    0.09
    第ä¸ĢåIJį
    0.09
    ãģ¶ãĤĬ
    0.09
    ãģĸ
    0.09
     Açık
    0.08
    dragon
    0.08
    Activations Density 0.324%

    No Known Activations