© 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. 13980
    Prev
    Next
    INDEX
    Explanations

    Gym | Chapter | Canada | Turbo | beauty | android

    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
    usted
    -0.18
    飫
    -0.18
    绣æĪĺ
    -0.18
    çĶŁäº§ä¼ģä¸ļ
    -0.18
     Sands
    -0.17
    åIJĥçļĦ
    -0.17
    èĽĨ
    -0.17
     statically
    -0.17
    åĸľæ¬¢åIJĥ
    -0.17
    umont
    -0.17
    POSITIVE LOGITS
    çĭ¬æľīçļĦ
    0.27
    çī¹æľīçļĦ
    0.22
    ä¸ĵçĶ¨
    0.21
    亲
    0.20
    -wide
    0.20
    riba
    0.20
    ä¸ĵå±ŀ
    0.20
     Shutdown
    0.20
    åĽĽåŃ£
    0.18
    åIJĦ
    0.18
    Activations Density 0.121%

    No Known Activations