© 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. 38754
    Prev
    Next
    INDEX
    Explanations

    prime minister

    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
    eness
    -0.11
    ĺ
    -0.10
    ảnh
    -0.10
    èµ·äºĨ
    -0.09
    æĨ§
    -0.09
    å¿Ŀ
    -0.09
    Ùħد
    -0.09
    walker
    -0.09
     Nation
    -0.09
    éĤ¨
    -0.09
    POSITIVE LOGITS
    åħ¼
    0.11
    ial
    0.10
    plier
    0.10
    aly
    0.09
    ieurs
    0.09
    æīĭä¸ŃçļĦ
    0.09
    ality
    0.08
    ive
    0.08
    Compat
    0.08
    iling
    0.08
    Activations Density 0.010%

    No Known Activations