© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1249
    Prev
    Next
    INDEX
    Explanations

    size and length

    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
    翻身
    -0.26
    ç»Ĩå¿ĥ
    -0.25
    .charAt
    -0.23
     invested
    -0.22
     HARD
    -0.22
     ResourceType
    -0.21
    crc
    -0.21
     Hardy
    -0.21
    æĬķèŀįèµĦ
    -0.21
     Busy
    -0.21
    POSITIVE LOGITS
     longer
    0.33
    éķ¿åº¦
    0.31
    æĽ´å¤§
    0.30
    尺寸
    0.29
    æłĩåĩĨ
    0.29
    ä¼łç»ŁçļĦ
    0.28
    æľĢéķ¿
    0.28
     sizes
    0.28
     traditional
    0.27
    延éķ¿
    0.27
    Activations Density 0.065%

    No Known Activations