© 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. 23515
    Prev
    Next
    INDEX
    Explanations

    an article followed by a noun

    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
    ìĹ´
    -0.10
    ä¸Ģ个å¤ļ
    -0.10
    fab
    -0.09
    æĪIJ为ä¸Ģ个
    -0.09
    è¿Ļ对
    -0.08
     Lars
    -0.08
    å¤ĩ
    -0.08
    æľ«
    -0.08
    çĶļ
    -0.08
    ä»ĸæĺ¯ä¸Ģ个
    -0.08
    POSITIVE LOGITS
     themselves
    0.11
    åĢij
    0.11
    罩
    0.10
    éĢłè¡Ģ
    0.09
    èĬ±äºĨ
    0.09
    éĢłçº¸
    0.09
    åĽ°
    0.08
    ами
    0.08
    sWith
    0.08
    ching
    0.08
    Activations Density 0.833%

    No Known Activations