© 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. 33438
    Prev
    Next
    INDEX
    Explanations

    neglect or neglectful action

    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
    ä¸Ŀ绸
    -0.09
    ä¸įä¸Ĭ
    -0.09
    kest
    -0.09
    ValueChanged
    -0.09
     gev
    -0.09
    人éĥ½
    -0.09
    جاÙĦ
    -0.09
    atically
    -0.09
    eries
    -0.08
    haar
    -0.08
    POSITIVE LOGITS
    å·²ä¹ħ
    0.13
    å·²ä¹ħçļĦ
    0.13
    ened
    0.11
    äºĨæĪijçļĦ
    0.11
    ively
    0.10
    ìĤ¬íķŃ
    0.10
    äºĨ好å¤ļ
    0.10
    eur
    0.10
    gable
    0.09
    ibrary
    0.09
    Activations Density 0.008%

    No Known Activations