© 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. 13034
    Prev
    Next
    INDEX
    Explanations

    opinions and views

    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
    eric
    -0.22
    æªĢ
    -0.21
    æĬ¥èĢĥ
    -0.21
    é¡¿
    -0.19
    uries
    -0.19
    .release
    -0.19
    jang
    -0.18
    umpt
    -0.18
     Chapters
    -0.17
    cir
    -0.17
    POSITIVE LOGITS
    è¨Ģ论
    0.27
     opinions
    0.24
     views
    0.24
    è§ĤçĤ¹
    0.24
    BCM
    0.22
    ä¸į代表
    0.22
    çļĦè§ĤçĤ¹
    0.21
    çģ¼
    0.20
    个人è§ĤçĤ¹
    0.20
    æĦıè§ģ
    0.20
    Activations Density 0.020%

    No Known Activations