© 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. 34974
    Prev
    Next
    INDEX
    Explanations

    Confederate or Federation

    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
    agna
    -0.09
    æ¸ħåĩī
    -0.08
    OURS
    -0.08
    æĬ¥è®°èĢħ
    -0.08
    uele
    -0.08
    ç£Ķ
    -0.08
    æĨĶ
    -0.08
    èĮ±
    -0.08
    iras
    -0.08
    æ´¼
    -0.08
    POSITIVE LOGITS
    olian
    0.10
    lector
    0.09
    xsd
    0.09
    ÑĪе
    0.09
    æķ´ä½ĵ
    0.08
    alborg
    0.08
    æĸ°æĿIJæĸĻ
    0.08
    çĶŁæ´»æĸ¹å¼ı
    0.08
    /custom
    0.08
    -leaning
    0.08
    Activations Density 0.013%

    No Known Activations