© 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. 11517
    Prev
    Next
    INDEX
    Explanations

    senate and legislators

    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
    滩
    -0.10
    æĿ¯
    -0.10
    INVAL
    -0.09
    横
    -0.09
    عت
    -0.09
    åħļåĨħ
    -0.09
    ablish
    -0.09
    akens
    -0.08
    .intValue
    -0.08
    ç¬Ķ
    -0.08
    POSITIVE LOGITS
    âĸ¹
    0.09
    åģľçĶµ
    0.09
    æĥĬåı¹
    0.09
    åij¨è½¬
    0.09
    ç¬ij容
    0.09
    anmar
    0.09
    eya
    0.09
    èĿİ
    0.09
    enez
    0.09
    ä¸Ģçľĭ
    0.09
    Activations Density 0.055%

    No Known Activations