© 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. 379
    Prev
    Next
    INDEX
    Explanations

    RPG games

    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
    aras
    -0.23
    æĭ¥æĬ¤
    -0.22
    hey
    -0.22
    asca
    -0.19
    resh
    -0.19
     mens
    -0.19
    æħķ
    -0.19
    åĨ¬å¥¥
    -0.19
    大åºĨ
    -0.19
    eful
    -0.18
    POSITIVE LOGITS
    bound
    0.24
    maker
    0.23
    naire
    0.22
    å®ĿèĹı
    0.22
    matic
    0.22
    ments
    0.21
    çªŁ
    0.21
     Dungeons
    0.21
    -solving
    0.21
    ®
    0.21
    Activations Density 0.004%

    No Known Activations