© 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. 15388
    Prev
    Next
    INDEX
    Explanations

    read more download

    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
    ãĢĴ
    -0.21
    ury
    -0.19
    utherland
    -0.19
    óc
    -0.18
    oku
    -0.17
    uppy
    -0.17
    -u
    -0.17
     Shed
    -0.17
    otr
    -0.17
     stab
    -0.16
    POSITIVE LOGITS
    æį®æѤ
    0.21
    ç½ij讯
    0.20
    çŁ¿ä¸ļ
    0.18
    åIJ¯åıij
    0.18
     subnet
    0.18
     context
    0.18
    å¾Ĵ
    0.18
    ç»Ĩèĩ´
    0.18
    è¿Ļ个éĹ®é¢ĺ
    0.18
    çŃĶå¤į
    0.17
    Activations Density 1.741%

    No Known Activations