© 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. 30632
    Prev
    Next
    INDEX
    Explanations

    at Ashton Gate

    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
    æĩĭ
    -0.09
    à°³
    -0.09
    UNET
    -0.08
     Bene
    -0.08
    çĽĪ
    -0.08
     anonymous
    -0.08
    åıªæĥ³
    -0.08
    èľĢ
    -0.08
    айд
    -0.08
     Jaw
    -0.08
    POSITIVE LOGITS
    ä¸ĭ车
    0.10
    åĮı
    0.09
    äºĮ线
    0.09
    ä¸ĭæ²ī
    0.09
    å·¡åĽŀ
    0.09
    å¿łå®ŀ
    0.09
    è¹ī
    0.09
    ä»İä¸ļ
    0.09
    ety
    0.08
    追赶
    0.08
    Activations Density 0.080%

    No Known Activations