© 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. 22785
    Prev
    Next
    INDEX
    Explanations

    arguing or debating

    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
    imming
    -0.09
    æģ¶
    -0.09
    ILES
    -0.09
    深深
    -0.08
    Coal
    -0.08
    anning
    -0.08
    害
    -0.08
    dens
    -0.08
    åı®
    -0.08
    è¡ĮåĬ¨
    -0.08
    POSITIVE LOGITS
    辩
    0.11
    è¦ģä¸įè¦ģ
    0.10
     Argument
    0.10
    ARG
    0.10
     contentious
    0.10
    äºī
    0.10
    æ±ŁåĮĹ
    0.10
    çĪŃ
    0.09
    äºī论
    0.09
    (argument
    0.09
    Activations Density 0.035%

    No Known Activations