© 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. 9162
    Prev
    Next
    INDEX
    Explanations

    spending on

    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
    顺便
    -0.09
    è¿Ľè¡Įåħ¨éĿ¢
    -0.09
    çī¡
    -0.09
    esters
    -0.09
    缮çļĦåľ¨äºİ
    -0.09
    æĬĬæı¡
    -0.09
    ç«ĭ足
    -0.09
    åIJĥåĪ°
    -0.08
    åݻ年
    -0.08
    enne
    -0.08
    POSITIVE LOGITS
    å¾Ĺèµ·
    0.11
    ä»Ģä¹Īåij¢
    0.11
    è¿Ļäºĭ
    0.10
    髯
    0.09
    çī¹å®ļ
    0.08
     tas
    0.08
     both
    0.08
    è¿Ļå¥Ĺ
    0.08
     this
    0.08
    è¿Ļç±»
    0.08
    Activations Density 0.017%

    No Known Activations