© 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. 13155
    Prev
    Next
    INDEX
    Explanations

    dating back to

    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
    Ä°M
    -0.21
    KHR
    -0.21
    éļıä¹ĭ
    -0.19
    èĮ´
    -0.19
    åĪĨéĴŁåIJİ
    -0.19
    çİ°
    -0.19
    è¿Łè¿Ł
    -0.18
    ê²łëĭ¤
    -0.18
     Geile
    -0.18
    ä¾£
    -0.18
    POSITIVE LOGITS
    ori
    0.20
    æľĢåĪĿ
    0.19
     Ive
    0.19
    ened
    0.19
    æľĢåĪĿçļĦ
    0.18
    å¤ļå¹´åīį
    0.18
    åĩłå¹´åīį
    0.18
    æºIJ头
    0.18
     years
    0.18
     infancy
    0.18
    Activations Density 0.017%

    No Known Activations