© 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. 404
    Prev
    Next
    INDEX
    Explanations

    time until / before / soon

    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
    æ¯ı次
    -0.25
    å¤ļ次
    -0.24
    once
    -0.24
    æ¯ı次éĥ½
    -0.23
     secre
    -0.23
    uv
    -0.23
    å½ĵæŶ
    -0.23
    ç»ıéªĮ
    -0.22
    com
    -0.22
    exe
    -0.22
    POSITIVE LOGITS
     foreseeable
    0.40
    å¾Īéķ¿
    0.34
    ä¸ĭåİ»
    0.32
    ä¸įä¼ļåĨį
    0.30
    æģIJæĢķ
    0.30
     indefinite
    0.30
     probably
    0.28
    èµ°ä¸ĭåİ»
    0.28
    èĩ³å°ij
    0.27
     onward
    0.26
    Activations Density 0.024%

    No Known Activations