© 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. 50380
    Prev
    Next
    INDEX
    Explanations

    black people

    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
     ÑĢазвиÑĤиÑı
    -0.10
    å¤©åºľ
    -0.09
    æľ¬äºº
    -0.09
    é¾Ľ
    -0.09
    ä¸ŃåĽ½æ±½è½¦
    -0.09
    éĴ»çłĶ
    -0.09
    ãĤ·ãĥ¼
    -0.09
    thy
    -0.08
    ego
    -0.08
    åı¦ä¸ĢåįĬ
    -0.08
    POSITIVE LOGITS
    ened
    0.09
    zel
    0.09
    plevel
    0.09
    é»į
    0.09
    .Unity
    0.09
    estroy
    0.09
    owned
    0.08
    /black
    0.08
    èĩªåĬ¨
    0.08
    ivas
    0.08
    Activations Density 0.022%

    No Known Activations