© 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. 246
    Prev
    Next
    INDEX
    Explanations

    fantasy/fiction place names

    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
     gang
    -0.25
    梢
    -0.25
    ercul
    -0.23
    gang
    -0.23
    éļĶ离
    -0.23
    åĮĹ京å¸Ĥ
    -0.23
    车åºĵ
    -0.23
     NAS
    -0.23
     NYPD
    -0.23
    åĽ¢ä½ĵ
    -0.23
    POSITIVE LOGITS
    æī§æĶ¿
    0.27
     Dungeons
    0.25
    urgy
    0.25
     xứ
    0.24
    æĶ¹éĿ©åıijå±ķ
    0.24
     Tell
    0.24
    дан
    0.23
    istik
    0.23
    sWith
    0.23
    Alchemy
    0.23
    Activations Density 0.031%

    No Known Activations