© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10592
    Prev
    Next
    INDEX
    Explanations

    tissue tumors and sarcomas

    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
    çĽı
    -0.23
     Feinstein
    -0.20
    æ¸ħåĩĢ
    -0.20
    cup
    -0.20
    equip
    -0.19
    illac
    -0.19
    _emit
    -0.19
    vak
    -0.19
    峨
    -0.19
    æĤ¬æµ®
    -0.19
    POSITIVE LOGITS
     minded
    0.20
    çİ©åħ·
    0.20
    èĤĮèĤī
    0.20
    tors
    0.19
     tors
    0.19
    ä¿ij
    0.19
     Toys
    0.19
    èµĦ产
    0.18
    èĤī
    0.18
    تÙĪر
    0.18
    Activations Density 0.123%

    No Known Activations