© 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. 61823
    Prev
    Next
    INDEX
    Explanations

    war, battle, soldiers

    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
     Arrest
    -0.09
    лим
    -0.09
    ä»Ļ
    -0.08
    (.)
    -0.07
     harmon
    -0.07
    chal
    -0.07
    Restr
    -0.07
    éĽħ
    -0.07
    çªľ
    -0.07
    beg
    -0.07
    POSITIVE LOGITS
    åĨĽäºĭ
    0.17
    æĪĺçķ¥
    0.16
    æĪĺæľ¯
    0.16
    çļĦæĪĺçķ¥
    0.15
    ä½ľæĪĺ
    0.14
    å¼ĢæĪĺ
    0.14
    å®ŀæĪĺ
    0.14
    æīĵä»Ĺ
    0.14
    æĪĺäºī
    0.14
    åĨĽäºº
    0.13
    Activations Density 0.140%

    No Known Activations