© 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. 3151
    Prev
    Next
    INDEX
    Explanations

    impressive qualities

    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
    hood
    -0.22
    IAL
    -0.21
    tiny
    -0.21
    éĩįçĤ¹åħ³æ³¨
    -0.21
    leigh
    -0.20
    ä¸Ģ个æĸ°çļĦ
    -0.20
    è§īå¾Ĺå¾Ī
    -0.19
    wards
    -0.19
    çĶŁæ´»
    -0.19
    ton
    -0.19
    POSITIVE LOGITS
     feats
    0.37
     feat
    0.34
     strides
    0.33
    -looking
    0.29
     enough
    0.28
     stature
    0.26
    壮è§Ĥ
    0.24
    -packed
    0.23
    ãģªãģĬ
    0.23
    ment
    0.22
    Activations Density 0.005%

    No Known Activations