© 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. 31832
    Prev
    Next
    INDEX
    Explanations

    body parts

    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
    èĢĮä¸Ķè¿ĺ
    -0.11
    å°¾
    -0.10
    ä½ĵåĨħ
    -0.10
    èĬ±æł·
    -0.10
    .tail
    -0.09
     Tail
    -0.09
    æĭĽ
    -0.09
    æĺŃ
    -0.09
     tail
    -0.09
    尾巴
    -0.09
    POSITIVE LOGITS
    ä¸Ģè§Ī
    0.10
    å·¥ä½ľç»ıéªĮ
    0.10
    éĥ¨éķ¿
    0.09
     bumped
    0.09
    ç´łè´¨
    0.09
     blot
    0.09
    åºķèķ´
    0.09
    åįľ
    0.09
    ä¸ĬçļĦ
    0.09
    ä»İæѤ
    0.09
    Activations Density 0.054%

    No Known Activations