© 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. 1159
    Prev
    Next
    INDEX
    Explanations

    amount of

    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
    æľĢåIJĪéĢĤ
    -0.24
    大çĪ·
    -0.23
    çĽijäºĭä¼ļ
    -0.23
    穷人
    -0.23
    éĿ¢ä¸´çļĦ
    -0.23
    èĩ³äºİ
    -0.22
    æĶ¶è´¹æłĩåĩĨ
    -0.22
    éĤ£å¤©
    -0.22
    带æĿ¥çļĦ
    -0.21
    åľ¨æİ¥åıĹ
    -0.21
    POSITIVE LOGITS
     information
    0.40
     effort
    0.34
     energy
    0.32
     evidence
    0.32
     paperwork
    0.31
     variability
    0.31
     flexibility
    0.31
     overlap
    0.31
     functionality
    0.30
     informatie
    0.30
    Activations Density 0.082%

    No Known Activations