© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50630
    Prev
    Next
    INDEX
    Explanations

    path, way, off

    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
    éĨ¯
    -0.09
    å·§
    -0.09
    antino
    -0.09
    çĦ¶æĺ¯
    -0.09
    пиÑģ
    -0.08
    å¡«åĨĻ
    -0.08
    çĭ¡
    -0.08
    hell
    -0.08
    礼æĭľ
    -0.08
     оÑĦоÑĢм
    -0.08
    POSITIVE LOGITS
    主æµģ
    0.18
     mainstream
    0.12
    寻常
    0.09
    æŃ£å¸¸çļĦ
    0.09
     path
    0.09
    大ä¼Ĺ
    0.09
     Andr
    0.09
    大åŁİå¸Ĥ
    0.09
    ä¸Ńéĥ¨
    0.09
    å°ĭ
    0.09
    Activations Density 0.007%

    No Known Activations