© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10317
    Prev
    Next
    INDEX
    Explanations

    weight, overweight, gain, management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    íĹĢ
    -0.22
    æľĢå¤ļçļĦ
    -0.20
     Frequency
    -0.19
    ÅĽcie
    -0.19
    åŃ¢
    -0.18
    .Summary
    -0.18
    wares
    -0.18
    ocale
    -0.18
    uvw
    -0.18
    æ°Ķæ°Ľ
    -0.18
    POSITIVE LOGITS
    éĹ®é¢ĺæĺ¯
    0.23
    ĵį
    0.22
    çĺ¦èº«
    0.21
    ¶
    0.21
    bane
    0.21
    身æĿIJ
    0.20
    ä½ĵéĩį
    0.20
    аÑĢÑĮ
    0.20
    æ³Ĭ
    0.20
    /body
    0.20
    Activations Density 0.044%

    No Known Activations