© 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. 1569
    Prev
    Next
    INDEX
    Explanations

    fascist, nationalist, or extremist groups

    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
    èī¯å¿ĥ
    -0.11
    onian
    -0.10
    人çĶŁçļĦ
    -0.09
    åĬŁå¤«
    -0.09
    çħ§é¡¾
    -0.09
    æĸ¯åŁº
    -0.09
    å¦ĥ
    -0.09
    лаÑģ
    -0.09
    工夫
    -0.08
    åį¯
    -0.08
    POSITIVE LOGITS
    åı³
    0.10
    çļĦ强大
    0.09
     powerful
    0.09
    ä»ĩæģ¨
    0.09
    .Driver
    0.09
    强大çļĦ
    0.09
    çIJ¥
    0.09
    èģļåIJĪ
    0.09
    çħ½
    0.09
    ulls
    0.09
    Activations Density 0.118%

    No Known Activations