© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52481
    Prev
    Next
    INDEX
    Explanations

    re-election campaign

    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
    æł·
    -0.10
    åݻ买
    -0.09
     swallow
    -0.09
    è¡Ķ
    -0.09
    åIJįæł¡
    -0.09
    åĬ£
    -0.09
    é¾Ļ头
    -0.09
    åķĥ
    -0.09
    edBy
    -0.09
    åѦ龸
    -0.09
    POSITIVE LOGITS
    Stick
    0.08
     stripe
    0.08
    èļ¤
    0.08
    uable
    0.08
     Stress
    0.08
    aniu
    0.08
     stress
    0.08
    leur
    0.08
    èľĺèĽĽ
    0.08
    *)&
    0.08
    Activations Density 0.003%

    No Known Activations