© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51653
    Prev
    Next
    INDEX
    Explanations

    wing politicization

    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
    é£İå°ļ
    -0.10
    sing
    -0.10
    Ñħод
    -0.09
     phá»ij
    -0.09
    çĸ¤
    -0.09
    主義
    -0.09
    主ä¹ī
    -0.09
    ãģĦãģĨ
    -0.09
    åķ¡
    -0.09
    ween
    -0.09
    POSITIVE LOGITS
    lish
    0.11
    tip
    0.10
    ester
    0.10
    åĦ¿
    0.10
    ł
    0.10
    деÑģÑıÑĤ
    0.10
    Executable
    0.10
    fully
    0.10
    ly
    0.09
    tower
    0.09
    Activations Density 0.008%

    No Known Activations