© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 368
    Prev
    Next
    INDEX
    Explanations

    original or adaptation/version

    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
    æĿŁ
    -0.28
     compt
    -0.25
    å¡ijæĸĻ
    -0.25
    å¢ŀéķ¿
    -0.24
     kickoff
    -0.23
    éļıæĹ¶
    -0.23
    ä¸ĭ次
    -0.23
    æºIJæºIJ
    -0.22
    /products
    -0.22
    éļıå¤Ħ
    -0.22
    POSITIVE LOGITS
    åİŁèijĹ
    0.48
    æĶ¹ç¼ĸ
    0.47
     original
    0.45
    æĶ¹åĬ¨
    0.42
    åĪł
    0.42
     adaptation
    0.39
     adaptations
    0.39
    çīĪæľ¬
    0.37
     version
    0.36
    original
    0.36
    Activations Density 0.047%

    No Known Activations