© 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. 12934
    Prev
    Next
    INDEX
    Explanations

    pituitary and thyroid conditions

    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
     crossings
    -0.23
    æľĢå¿«çļĦ
    -0.21
    çIJµ
    -0.21
    çĪ¶åŃIJ
    -0.19
    污æŁĵéĺ²æ²»
    -0.19
    å¿¿
    -0.19
    棺
    -0.19
    orta
    -0.18
    ocard
    -0.18
    客
    -0.18
    POSITIVE LOGITS
     adrenal
    0.25
     cush
    0.25
    æ½®
    0.24
    失è°ĥ
    0.23
     Clamp
    0.21
    è¡°
    0.21
    balances
    0.20
     abnormalities
    0.20
     hyper
    0.20
    æľīèī²
    0.20
    Activations Density 0.161%

    No Known Activations