© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3168
    Prev
    Next
    INDEX
    Explanations

    what you want to know

    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
    Negative Logits
     vh
    -0.24
    ents
    -0.24
     Compound
    -0.23
    vh
    -0.23
    éľ²å¤©
    -0.22
    ’autres
    -0.22
    'autres
    -0.22
    åıªæĺ¯ä¸ºäºĨ
    -0.21
    æ·Į
    -0.21
    chen
    -0.21
    POSITIVE LOGITS
    为ä»Ģä¹Ī
    0.27
     why
    0.26
    ä¹ŁæŃ£æĺ¯
    0.25
    wed
    0.23
    -SA
    0.23
    çļĦä¸Ģ大
    0.22
    åIJĹ
    0.22
     fodder
    0.22
     viewType
    0.22
     happening
    0.22
    Activations Density 0.138%

    No Known Activations