© 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. 3303
    Prev
    Next
    INDEX
    Explanations

    past time periods

    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
     undisclosed
    -0.33
     kindly
    -0.28
     team
    -0.28
    æľ¬æľĪ
    -0.28
    éĹ®ä»ĸ
    -0.27
     morning
    -0.27
     personally
    -0.27
     fortn
    -0.26
     unspecified
    -0.26
     tonight
    -0.26
    POSITIVE LOGITS
    åIJİæĿ¥
    0.44
    åĩłåįģå¹´
    0.42
    æĶ¹éĿ©å¼ĢæĶ¾
    0.42
     decades
    0.41
    ä¸Ĭä¸ĸ纪
    0.41
    éĢIJæ¸IJ
    0.40
    å·¥ä¸ļåĮĸ
    0.40
    åħ´èµ·
    0.40
    éĤ£æŶåĢĻ
    0.40
    åĪĨåĮĸ
    0.38
    Activations Density 0.221%

    No Known Activations