© 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. 57619
    Prev
    Next
    INDEX
    Explanations

    weapons and ordnance

    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
    åŀ«
    -0.10
    æľĭåıĭ们
    -0.10
    ä¸įæĺ¯ä¸Ģ个
    -0.10
    _Struct
    -0.09
     Elegant
    -0.08
    人家
    -0.08
    娥
    -0.08
    åŀĥ
    -0.08
    elen
    -0.08
    วà¸Ķ
    -0.08
    POSITIVE LOGITS
    amins
    0.09
    鼨
    0.09
    èķī
    0.09
    æİ·
    0.09
    kie
    0.09
    åĽŀåIJĪ
    0.09
    æĵį
    0.09
    alc
    0.08
    afx
    0.08
    clip
    0.08
    Activations Density 0.013%

    No Known Activations