© 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. 3165
    Prev
    Next
    INDEX
    Explanations

    leaning towards or lean variations

    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
    rix
    -0.23
    تاÙĨ
    -0.23
    lications
    -0.20
    -thirds
    -0.20
    ivity
    -0.20
    çĽijäºĭä¼ļ
    -0.20
    nal
    -0.19
    kinson
    -0.19
    迹
    -0.19
    æĪijæĥ³
    -0.19
    POSITIVE LOGITS
    er
    0.22
     towards
    0.22
     toward
    0.21
    ingly
    0.20
    est
    0.20
    ãģĵãģ¨
    0.19
     Towards
    0.19
    ToWorld
    0.19
    NING
    0.18
    .protobuf
    0.18
    Activations Density 0.017%

    No Known Activations