© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15347
    Prev
    Next
    INDEX
    Explanations

    capsule endoscopy and formulations

    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
    fully
    -0.21
    ubar
    -0.18
    liness
    -0.17
    quam
    -0.17
    佬
    -0.16
    ëł¹
    -0.16
    è¢Ĥ
    -0.16
    enticator
    -0.15
    loom
    -0.15
    ened
    -0.15
    POSITIVE LOGITS
    ary
    0.25
    hip
    0.18
    ity
    0.18
    ilia
    0.18
    累累
    0.17
    åŃIJéĩĮ
    0.17
    å¼ıçļĦ
    0.17
    æľŁ
    0.17
    arian
    0.17
    ists
    0.16
    Activations Density 0.021%

    No Known Activations