© 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. 10367
    Prev
    Next
    INDEX
    Explanations

    Star Wars characters

    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
    çĭİ
    -0.21
     wild
    -0.20
    éĩİ
    -0.20
    elled
    -0.19
    nel
    -0.19
     ny
    -0.18
    éĵĥ
    -0.18
    ni
    -0.18
    HashCode
    -0.18
    Ny
    -0.17
    POSITIVE LOGITS
     Darth
    0.20
     Dominion
    0.19
    etical
    0.18
    iji
    0.18
    è¯Ńæ°Ķ
    0.17
    åı£æ°Ķ
    0.17
    èĤº
    0.17
    çŁ¥éģĵèĩªå·±
    0.17
    auce
    0.17
    -transform
    0.16
    Activations Density 0.001%

    No Known Activations