© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16310
    Prev
    Next
    INDEX
    Explanations

    cr require separate respiratory

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Dress
    -0.24
     dress
    -0.23
    osity
    -0.22
     tanks
    -0.21
    éĽķ
    -0.21
     Tanks
    -0.21
    ç©¿ä¸Ĭ
    -0.20
     Rust
    -0.20
    .words
    -0.20
    è¢į
    -0.20
    POSITIVE LOGITS
    ãĤ¨ãĥįãĥ«
    0.28
    åħħçĶµ
    0.27
    çĶµéĩı
    0.27
     bezpo
    0.25
    çĶµæºIJ
    0.25
     Accessories
    0.23
    æĤŃ
    0.23
    çĶµåĬĽ
    0.23
    æĽ´å¿«
    0.23
    æİ¥åħ¥
    0.22
    Activations Density 0.023%

    No Known Activations