© 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. 11238
    Prev
    Next
    INDEX
    Explanations

    lymphocytic leukemia

    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
    建
    -0.21
    æľĶ
    -0.20
     excer
    -0.19
    è¢Ħ
    -0.19
    èĶļ
    -0.19
     shim
    -0.19
    æĸ¯å¡Ķ
    -0.18
    ä½ĵåĬĽ
    -0.18
    åĴ
    -0.18
    åľŁ
    -0.17
    POSITIVE LOGITS
    maf
    0.24
    yy
    0.22
    sen
    0.21
    erg
    0.20
    åľ¨é¦Ļ港
    0.19
    gy
    0.19
    Bubble
    0.19
    eral
    0.18
    æºIJæºIJä¸įæĸŃ
    0.18
     Mandarin
    0.17
    Activations Density 0.003%

    No Known Activations