© 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. 48962
    Prev
    Next
    INDEX
    Explanations

    aggressive behavior, conflict, war, winners

    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
    æı
    -0.09
    åıĤè°ĭ
    -0.09
     pays
    -0.09
    åѦä¸ļ
    -0.08
     deport
    -0.08
     Pays
    -0.08
     Intelligence
    -0.07
     spl
    -0.07
     spies
    -0.07
    缩çŁŃ
    -0.07
    POSITIVE LOGITS
    财产
    0.12
    产æĿĥ
    0.12
    夺åıĸ
    0.12
    éĺ²åį«
    0.12
    夺
    0.12
    æļ´åĬĽ
    0.11
    éĺ²æĬ¤
    0.10
    æĬ¢åĬ«
    0.10
    没æĶ¶
    0.10
    -property
    0.10
    Activations Density 0.065%

    No Known Activations