© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 170
    Prev
    Next
    INDEX
    Explanations

    arrested

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    æŁĶåĴĮ
    -0.24
    aldi
    -0.23
     warm
    -0.22
     umbrella
    -0.22
     wisely
    -0.21
     warmer
    -0.21
     warming
    -0.21
    课åłĤæķĻåѦ
    -0.21
    ensem
    -0.21
    ragon
    -0.21
    POSITIVE LOGITS
    åĪij
    0.26
    è®°å½ķ
    0.26
    ç¼ĸåı·
    0.25
    åĽłä¸ºä»ĸ
    0.25
     uploaded
    0.25
     record
    0.25
    å½ķ
    0.24
    æ¯Ĵåĵģ
    0.24
     detention
    0.23
    泪
    0.23
    Activations Density 0.004%

    No Known Activations