© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2659
    Prev
    Next
    INDEX
    Explanations

    actor or actress portrayal

    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
    ä¿¡çĶ¨
    -0.26
     ÑħозÑıй
    -0.24
     Datum
    -0.24
    é¹Ħ
    -0.23
    ä¸ĩ象
    -0.23
    æĵ¦æĭŃ
    -0.22
    éļıæľº
    -0.22
     <<-
    -0.22
     sidelines
    -0.22
    Datum
    -0.21
    POSITIVE LOGITS
     representation
    0.45
     representations
    0.42
     modeling
    0.40
    Representation
    0.39
     Representation
    0.37
    模æĭŁ
    0.36
    模仿
    0.36
    _representation
    0.36
     portrayal
    0.36
    representation
    0.36
    Activations Density 0.333%

    No Known Activations