© 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. 21190
    Prev
    Next
    INDEX
    Explanations

    early start or beginning

    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
    è¿ĺæĺ¯ä¼ļ
    -0.10
    忽
    -0.08
    æŶ任
    -0.08
     Cow
    -0.08
    æĥħå½¢
    -0.08
    å¯Ł
    -0.08
    åħľ
    -0.08
    缮çļĦåľ¨äºİ
    -0.08
    åĨĽäºº
    -0.08
    ä¸Ģå¤ľ
    -0.08
    POSITIVE LOGITS
    å°½æĹ©
    0.24
    æıIJæĹ©
    0.23
    æĹ©æĹ©
    0.21
    æıIJåīį
    0.19
    æĹ©æĹ¥
    0.18
    æĹ©åľ¨
    0.18
    æĹ©çĤ¹
    0.16
    æĹ©
    0.16
    early
    0.15
    æĹ©å°±
    0.15
    Activations Density 0.075%

    No Known Activations