© 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. 15857
    Prev
    Next
    INDEX
    Explanations

    conjunctions after punctuation

    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
    ãģ§ãģĻãĤĪ
    -0.22
    ä¼ģä¸ļæıIJä¾Ľ
    -0.19
    oman
    -0.18
    alone
    -0.18
    è¶Ĭæĺ¯
    -0.18
     MAD
    -0.18
    èĭı
    -0.18
     tob
    -0.18
    ãģ§ãģĻãģĹ
    -0.18
    adt
    -0.17
    POSITIVE LOGITS
    è¿ĻäºĽéĥ½æĺ¯
    0.33
     etc
    0.29
    çŃīæĥħåĨµ
    0.29
    çŃīçŃī
    0.28
    è¿Ļ两个
    0.26
    è¿Ļ两
    0.25
    çŃīéĹ®é¢ĺ
    0.24
    çŃīæĸ¹éĿ¢
    0.24
    çŃīåĽłç´ł
    0.23
    çŃīåİŁåĽł
    0.23
    Activations Density 0.224%

    No Known Activations