© 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. 10737
    Prev
    Next
    INDEX
    Explanations

    ladies and gentlemen, Mr

    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
    antal
    -0.21
    Edited
    -0.20
    ä¸įæĩĤ
    -0.20
    attached
    -0.19
    颦
    -0.19
    æľªæĿ¥çļĦ
    -0.18
    æĹ¥è®°
    -0.18
    åĴ¨è¯¢æľįåĬ¡
    -0.18
    æĢĿç´¢
    -0.18
    insky
    -0.18
    POSITIVE LOGITS
    éħĴ
    0.20
    確ãģĭãģ«
    0.19
    beer
    0.19
    ãģĽ
    0.19
    ä¸»åľº
    0.19
    slick
    0.19
    饮éħĴ
    0.18
    座ä½į
    0.18
    æĪijèĥ½
    0.18
    åıĬ缸åħ³
    0.18
    Activations Density 0.022%

    No Known Activations