© 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. 12827
    Prev
    Next
    INDEX
    Explanations

    corneal perforation

    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
    èĩªå¦Ĥ
    -0.22
    å©Ĩ
    -0.21
     Ups
    -0.20
    sst
    -0.20
    shr
    -0.19
    è´¯
    -0.19
    Enlarge
    -0.19
    มวล
    -0.18
    ableObject
    -0.18
     Affero
    -0.17
    POSITIVE LOGITS
    çĴŀ
    0.20
     лиÑĨа
    0.20
     иÑģÑĤ
    0.19
    .paths
    0.19
     surface
    0.19
     оÑĩеÑĢ
    0.18
    çĴ¨
    0.18
    éªħ
    0.18
    eters
    0.18
    çĭ®
    0.18
    Activations Density 0.034%

    No Known Activations