© 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. 8684
    Prev
    Next
    INDEX
    Explanations

    becoming associated with

    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
    æĬĬè¿ĻäºĽ
    -0.10
    èle
    -0.10
    è¿ĻäºĽ
    -0.09
    æĬĬè¿Ļ个
    -0.09
    è¿Ļæī¹
    -0.09
    æ±²
    -0.09
    æºĥ
    -0.09
    èĥ¸æĢĢ
    -0.09
    IndexOf
    -0.08
    SourceType
    -0.08
    POSITIVE LOGITS
    ä½ľä¸ºä¸Ģç§į
    0.11
    çĶŁåij½åĬĽ
    0.10
    ढ
    0.10
    åıijæĮ¥ä½ľçĶ¨
    0.10
    çļĦåľ°ä½į
    0.10
    å¤ļåĬŁèĥ½
    0.09
    åĬŁçĶ¨
    0.09
    åıijæĮ¥
    0.09
     имени
    0.09
    è½½
    0.09
    Activations Density 0.392%

    No Known Activations