© 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. 48503
    Prev
    Next
    INDEX
    Explanations

    military presence and foreign relations

    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
    å¼ĢåĬŀ
    -0.09
    çıł
    -0.09
    ç«ŀäºī
    -0.08
    è·ij
    -0.08
     group
    -0.08
    çĶŁæĢģåľĪ
    -0.08
     Hod
    -0.08
    ä½¼
    -0.08
    太太
    -0.08
    æ·«
    -0.08
    POSITIVE LOGITS
    çī¹æ´¾
    0.11
    æı´
    0.11
    _deploy
    0.11
    åĨ³çŃĸéĥ¨ç½²
    0.11
    ä¼Ĭæĭīåħĭ
    0.10
    Foreign
    0.10
    æµ·å¤ĸ
    0.10
    deploy
    0.10
    å¤ĸ交
    0.10
    éĥ¨ç½²
    0.10
    Activations Density 0.102%

    No Known Activations