© 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. 920
    Prev
    Next
    INDEX
    Explanations

    possessive followed by an attribute

    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
    æľªæĿ¥
    -0.23
    人大代表
    -0.22
    _DER
    -0.22
     fontStyle
    -0.22
     dj
    -0.21
    大纲
    -0.21
    dimensions
    -0.21
     Beat
    -0.20
    èĥ¸æĢĢ
    -0.20
    Beat
    -0.20
    POSITIVE LOGITS
    å°ijéĩı
    0.28
     suppress
    0.25
     occasional
    0.25
    çĥ
    0.25
    åIJ¦
    0.24
    精彩çļĦ
    0.24
    类似
    0.23
     inability
    0.23
    "+"
    0.23
    ä¸įåĪ°ä½į
    0.23
    Activations Density 0.009%

    No Known Activations