© 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. 2818
    Prev
    Next
    INDEX
    Explanations

    rear and back parts of locations

    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¸ĩ个
    -0.26
    é¢Ĺ
    -0.26
    ä¸ĩ亿
    -0.26
    æĪIJè´¥
    -0.26
    ä¸ī峡
    -0.24
     beads
    -0.24
    å¹´ä¸ĬåįĬå¹´
    -0.24
     reigning
    -0.23
    çIJĨäºĭéķ¿
    -0.23
    éģ¨
    -0.23
    POSITIVE LOGITS
    åºŃéĻ¢
    0.27
    house
    0.27
     unlocked
    0.26
    party
    0.25
     kitchen
    0.25
     hire
    0.25
     garden
    0.24
     gardens
    0.24
     kitchens
    0.24
    åݨæĪ¿
    0.24
    Activations Density 0.006%

    No Known Activations