© 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. 50677
    Prev
    Next
    INDEX
    Explanations

    dominance and superiority

    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
    rollable
    -0.09
    æĪij们认为
    -0.08
    utsch
    -0.08
    è·¨çķĮ
    -0.08
    ä¸ĬãģĴ
    -0.08
    æĦŁçŁ¥
    -0.08
    ç»ļ丽
    -0.08
    rear
    -0.08
    enberg
    -0.08
    绿èī²çݯä¿Ŀ
    -0.08
    POSITIVE LOGITS
    æĶ¯éħį
    0.20
     dominance
    0.20
    龸
    0.18
    主导
    0.18
     Domin
    0.17
    主宰
    0.16
    Domin
    0.16
     dominant
    0.15
     domination
    0.15
     dominate
    0.14
    Activations Density 0.078%

    No Known Activations