© 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. 17158
    Prev
    Next
    INDEX
    Explanations

    gun, gunmen, Ranger, SNP

    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
    krit
    -0.20
    lie
    -0.19
    åĵģåij³
    -0.18
    稼
    -0.18
    åĵģ
    -0.18
    oner
    -0.17
    èįīæ¡Ī
    -0.16
    æĥ«
    -0.16
    sprites
    -0.16
    ings
    -0.16
    POSITIVE LOGITS
    åĪĢ
    0.19
    ç¥ī
    0.19
    кÑĢи
    0.18
     liá»ĩt
    0.18
    身亡
    0.18
    éĻį临
    0.18
    dom
    0.17
    etty
    0.17
    æģ£
    0.17
    ific
    0.16
    Activations Density 0.001%

    No Known Activations