© 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. 58433
    Prev
    Next
    INDEX
    Explanations

    military coup

    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
    çĪµ
    -0.10
    è°
    -0.10
    åij¨è¾¹
    -0.09
    ä¸Ģè§Ĵ
    -0.09
    hausen
    -0.08
    Pane
    -0.08
    ä¾ł
    -0.08
    ãģĹãģ¾
    -0.08
     confer
    -0.08
     tslib
    -0.08
    POSITIVE LOGITS
    äh
    0.09
     hel
    0.09
    è·µ
    0.08
    æľºåĻ¨
    0.08
    主æĿ¿
    0.08
     bend
    0.08
    æĹłäºº
    0.08
    æĹłå¿§
    0.08
    _cos
    0.08
     MACHINE
    0.08
    Activations Density 0.021%

    No Known Activations