© 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. 9041
    Prev
    Next
    INDEX
    Explanations

    uprising, civil war, revolution

    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
     ADS
    -0.10
    å¾Ģè¿Ķ
    -0.10
     nigeria
    -0.09
    é¹°
    -0.09
    åĺ±
    -0.08
    æİĪ
    -0.08
    urd
    -0.08
    婶
    -0.08
    èļĿ
    -0.08
    æŀģå°ij
    -0.08
    POSITIVE LOGITS
    Parcelable
    0.11
    举
    0.10
    itespace
    0.09
    imiters
    0.09
    ÐŁÐ¾Ð´ÑĢобнее
    0.09
    é¢Ĩ导人
    0.09
    æ²³åĮĹçľģ
    0.09
    éĹ¹
    0.08
    leader
    0.08
    å¤Ń
    0.08
    Activations Density 0.029%

    No Known Activations