© 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. 20885
    Prev
    Next
    INDEX
    Explanations

    I don't need to know

    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
    æľīè¶³å¤ŁçļĦ
    -0.10
    æ·ĭ
    -0.10
    建ç«ĭèµ·
    -0.09
     paperback
    -0.09
    弥补
    -0.08
    çĪ·çĪ·
    -0.08
    è¶³å¤Ł
    -0.08
    èĵ¼
    -0.08
    ç»ıåħ¸
    -0.08
    æµģ
    -0.08
    POSITIVE LOGITS
    说ä»Ģä¹Ī
    0.10
    psc
    0.10
    ami
    0.09
    æ²®
    0.09
    å¾¼
    0.09
    å¼Ģ头
    0.09
    .words
    0.09
    çĥ¦
    0.08
    糧
    0.08
    åĭĭ
    0.08
    Activations Density 0.069%

    No Known Activations