© 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. 36008
    Prev
    Next
    INDEX
    Explanations

    peace, war, normalization, treaty

    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
    濯
    -0.09
    æľĢå¤ļçļĦ
    -0.09
    æ´ģçĻ½
    -0.08
    ç¬Ħ
    -0.08
    aky
    -0.08
    st
    -0.08
    çīĮçħ§
    -0.08
    就读
    -0.08
    re
    -0.08
    çĶĦ
    -0.08
    POSITIVE LOGITS
    еÑĩа
    0.12
    ugu
    0.10
    /animate
    0.09
    峡
    0.09
    åıĶ
    0.09
    æŃ£å¼ı
    0.09
    Handles
    0.09
    _Button
    0.09
    SCII
    0.09
    ãĥ©ãĤ¤ãĥ³
    0.09
    Activations Density 0.035%

    No Known Activations