© 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. 3309
    Prev
    Next
    INDEX
    Explanations

    make... easier/safer/possible/fun

    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
     ?,
    -0.24
    ?,?,?,?,
    -0.24
     meanwhile
    -0.23
    éĶŃ
    -0.23
    )];↵
    -0.22
    }];↵
    -0.22
    åıijå±ķä¸Ń
    -0.22
    ched
    -0.21
    åį´è¢«
    -0.21
    ä½Ĩåį´
    -0.21
    POSITIVE LOGITS
    尤为éĩįè¦ģ
    0.30
     easier
    0.28
    尤为
    0.26
     necessary
    0.25
    åıĺå¾Ĺ
    0.25
    æijĨåľ¨
    0.24
    çļĦéĢīæĭ©
    0.24
     safer
    0.24
    æĽ´å®¹æĺĵ
    0.24
    稿
    0.24
    Activations Density 0.118%

    No Known Activations