© 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. 11669
    Prev
    Next
    INDEX
    Explanations

    Andalusian, Lusatian, Flemish, Tuscan, Thuringia

    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
    天涯
    -0.21
    åħļç»Ħ
    -0.18
     teasing
    -0.18
    vable
    -0.18
     bills
    -0.18
    å³Ĵ
    -0.18
    anas
    -0.18
    ipheral
    -0.17
    ichi
    -0.17
    驽
    -0.17
    POSITIVE LOGITS
    åľ°åĮºçļĦ
    0.27
    åľ°åĮº
    0.24
    çŃīåľ°
    0.24
    åľ°åįĢ
    0.22
     облаÑģÑĤÑĮ
    0.20
    åľŁåľ°
    0.20
    èĢģ家
    0.20
    ä¹ĥèĩ³
    0.20
     облаÑģÑĤи
    0.20
    èįīåľ°
    0.19
    Activations Density 0.064%

    No Known Activations