© 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. 16552
    Prev
    Next
    INDEX
    Explanations

    collection or anthology

    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
    æĬĢæľ¯äººåijĺ
    -0.22
    override
    -0.22
    æŃ¥éª¤
    -0.21
    icontrol
    -0.20
    æ¯Ķè¾ĥç®Ģåįķ
    -0.19
    åľ¨æİ¥åıĹ
    -0.19
    åľ¨çݩ家ä¸Ń
    -0.19
     override
    -0.19
    æĬ¥ä»ĩ
    -0.19
    è¾ĥ强
    -0.19
    POSITIVE LOGITS
    æ±ĩéĽĨ
    0.31
    æ±ĩèģļ
    0.23
    Containing
    0.23
    éĢīåıĸ
    0.22
    รวม
    0.22
    éĽĨç»ĵ
    0.21
     sampler
    0.21
    éĽĨåIJĪ
    0.21
     collection
    0.21
    åĮħåIJ«
    0.21
    Activations Density 0.070%

    No Known Activations