© 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. 48608
    Prev
    Next
    INDEX
    Explanations

    former leaders and public figures

    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
    æĬ¬å¤´
    -0.10
    ä¹ĭä¸Ĭ
    -0.10
    gle
    -0.09
    çĥ¦
    -0.09
    icers
    -0.08
    Asc
    -0.08
    çħ
    -0.08
    unce
    -0.08
    åľ¬
    -0.08
    lers
    -0.08
    POSITIVE LOGITS
     retired
    0.15
    æĽ¾ä»»
    0.14
     former
    0.14
    éĢĢä¼ij
    0.13
    éĢĢå½¹
    0.12
    æĺĶæĹ¥
    0.11
     cũ
    0.11
    former
    0.11
    Former
    0.11
    å½ĵå¹´
    0.11
    Activations Density 0.089%

    No Known Activations