© 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. 3308
    Prev
    Next
    INDEX
    Explanations

    financial services organizations

    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
    èĩªå¸¦
    -0.25
    liament
    -0.24
    伤亡
    -0.23
    该éĻ¢
    -0.23
    ADVERTISEMENT
    -0.22
    iegel
    -0.22
    åĨ°åĨ·
    -0.22
    åĺĺ
    -0.22
    èģĺ
    -0.22
    пÑĥ
    -0.22
    POSITIVE LOGITS
     FR
    0.24
    驳
    0.24
    é½IJ
    0.24
     Fro
    0.22
     Drops
    0.21
     conflict
    0.21
     Interpret
    0.21
    <Array
    0.21
    /Form
    0.21
     suppress
    0.21
    Activations Density 0.024%

    No Known Activations