© 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. 12141
    Prev
    Next
    INDEX
    Explanations

    carcinoid tumors

    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
    side
    -0.19
    çŁĽçĽ¾
    -0.19
     Meyer
    -0.18
    讨
    -0.18
    åı£åij³
    -0.18
    ium
    -0.18
    è¨İ
    -0.18
    unset
    -0.17
    åħ¼
    -0.17
    æĢ¨
    -0.17
    POSITIVE LOGITS
    ooting
    0.19
    ledo
    0.19
    áŀĦ
    0.19
    ä¸įå®Į
    0.18
    ç¯ģ
    0.17
     Afr
    0.17
    æĿ¥ä¸įåıĬ
    0.17
    entrant
    0.17
    mitter
    0.17
    声åĵį
    0.17
    Activations Density 0.001%

    No Known Activations