© 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. 3377
    Prev
    Next
    INDEX
    Explanations

    all or everyone for a group

    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
    çŃīæ´»åĬ¨
    -0.22
    IID
    -0.22
    ãģŁãĤĬ
    -0.21
    ãģľ
    -0.21
     hus
    -0.21
    çŃīæĥħåĨµ
    -0.21
     entirely
    -0.20
    ä½łä»¥ä¸º
    -0.20
    åĬ¨éĿĻ
    -0.20
     revolutions
    -0.19
    POSITIVE LOGITS
    è°ģ
    0.33
     whoever
    0.28
     who
    0.28
     involved
    0.26
     mankind
    0.26
     кÑĤо
    0.25
     regardless
    0.25
    è°ģèĥ½
    0.25
    æĢģ
    0.24
     Interested
    0.24
    Activations Density 0.030%

    No Known Activations