© 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. 23271
    Prev
    Next
    INDEX
    Explanations

    spoon.com or Spooner

    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
    æĬ¥å¤į
    -0.10
    ANA
    -0.09
    uar
    -0.09
    å°±è¿ŀ
    -0.09
    ually
    -0.09
    çįŃ
    -0.09
    ä»İæł¹æľ¬ä¸Ĭ
    -0.09
    æīĭå¥Ĺ
    -0.09
    apur
    -0.09
    scape
    -0.09
    POSITIVE LOGITS
    ful
    0.13
    éĻIJãĤĬ
    0.10
    åĵĩ
    0.10
    èĩ¾
    0.10
    ç¾¹
    0.10
    èĥĻ
    0.09
    åĮĻ
    0.09
    èĪĢ
    0.09
    holding
    0.09
    ertino
    0.09
    Activations Density 0.004%

    No Known Activations