© 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. 12717
    Prev
    Next
    INDEX
    Explanations

    formation of thunderstorms and combustion

    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
    @update
    -0.28
     пÑĢиÑıÑĤн
    -0.24
    _ComCallableWrapper
    -0.24
    Ctrls
    -0.23
    ocols
    -0.23
    oload
    -0.23
    	RTLR
    -0.22
     заÑĢегиÑģÑĤ
    -0.22
     минималÑĮн
    -0.22
    åĿĩ使åħ¶
    -0.22
    POSITIVE LOGITS
    çݰ象
    0.26
     phenomenon
    0.26
    æĺ¯åĽłä¸º
    0.25
     formation
    0.25
     formations
    0.25
    è¿Ļæĺ¯åĽłä¸º
    0.24
    å·§åIJĪ
    0.23
    åĽłä¸ºåľ¨
    0.23
    è¿Ļç§įæĥħåĨµ
    0.23
    èīºæľ¯åĵģ
    0.23
    Activations Density 0.096%

    No Known Activations