© 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. 17077
    Prev
    Next
    INDEX
    Explanations

    Pixar, Cruise, Olympics, Copyright

    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
    kest
    -0.22
    麻辣
    -0.21
    åħ¨å®¶
    -0.21
    åłµ
    -0.21
    ays
    -0.18
    educ
    -0.18
    .PrimaryKey
    -0.18
     agency
    -0.18
     compens
    -0.18
    acas
    -0.18
    POSITIVE LOGITS
    çŀ§
    0.21
    èĬ¬åħ°
    0.21
    çķĮéĻIJ
    0.20
     fontStyle
    0.20
    管å§Ķä¼ļ
    0.20
    öl
    0.19
    èµ·çĤ¹
    0.19
    änn
    0.19
    åIJĦåĽ½
    0.19
    terraform
    0.19
    Activations Density 0.003%

    No Known Activations