© 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. 19790
    Prev
    Next
    INDEX
    Explanations

    continuous use or operation

    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
    åijĬåĪ«
    -0.09
    家éĩĮ
    -0.09
    onia
    -0.09
    Infinity
    -0.09
    广大群ä¼Ĺ
    -0.08
    çľ¼éĩĮ
    -0.08
    åħ»
    -0.08
    èĢĹ
    -0.08
    å¸Ŀ
    -0.08
    çĺģ
    -0.08
    POSITIVE LOGITS
    è¿ŀç»Ń
    0.21
    ä¸įéĹ´æĸŃ
    0.18
     continuous
    0.17
    éĢ£çºĮ
    0.16
    continuous
    0.16
    _continuous
    0.16
    Continuous
    0.15
     Continuous
    0.13
     uninterrupted
    0.13
    ä¸įéĹ´
    0.13
    Activations Density 0.099%

    No Known Activations