© 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. 13686
    Prev
    Next
    INDEX
    Explanations

    ocular and corneal tissues

    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
    åºķçĽĺ
    -0.23
    æıĨ
    -0.22
     JAXB
    -0.21
    éĩįæķ´
    -0.21
     backbone
    -0.21
    riba
    -0.21
    èĥ¸åı£
    -0.20
    æķ²
    -0.20
    çĺ¦èº«
    -0.19
    è°ĥçIJĨ
    -0.19
    POSITIVE LOGITS
    çľ¼ç§ij
    0.50
    çľ¼éĥ¨
    0.46
    è§ĨåĬĽ
    0.45
    åħīåѦ
    0.44
     eye
    0.42
    çľ¼çĿĽ
    0.42
    çľ¼
    0.41
    çľ¼çIJĥ
    0.41
    -eyed
    0.40
    çļĦçľ¼çĿĽ
    0.40
    Activations Density 0.406%

    No Known Activations