© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12340
    Prev
    Next
    INDEX
    Explanations

    St. Thomas

    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
    è¾ħ
    -0.22
    缸çĪ±
    -0.19
     getChild
    -0.19
    æį¢ä¸ª
    -0.19
    æĴ¤ç¦»
    -0.19
    åµĮ
    -0.18
    éĤº
    -0.18
    PG
    -0.17
    иÑĩеÑģÑĤво
    -0.17
    å¤ļ人
    -0.17
    POSITIVE LOGITS
     myself
    0.35
    ä½Ĩæĺ¯æĪij
    0.26
     personally
    0.26
    ä½ĨæĪij
    0.25
    æīĢ以æĪij
    0.25
    æĪijèĩªå·±
    0.23
    æ·±çŁ¥
    0.21
    ç¥ĸåĽ½
    0.21
     erg
    0.21
    åĽłä¸ºæĪij
    0.21
    Activations Density 0.196%

    No Known Activations