© 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. 12626
    Prev
    Next
    INDEX
    Explanations

    what happened to

    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
    ä¸Ģå®ļçļĦ
    -0.22
    æĬ½
    -0.21
    æĺİå¹´
    -0.21
    åĽŀåºĶ
    -0.20
     Pru
    -0.19
    é»ijå¤ľ
    -0.19
    诱æĥij
    -0.19
    Kit
    -0.18
    æ¸Ĭ
    -0.18
    üz
    -0.17
    POSITIVE LOGITS
    ä¸įè§ģäºĨ
    0.26
    Lost
    0.23
    lost
    0.21
     lost
    0.21
    失踪
    0.21
     ÑģобÑģÑĤвенно
    0.20
    å¤©çľŁ
    0.20
     Lost
    0.20
    ober
    0.19
    éĤ£æ®µ
    0.18
    Activations Density 0.013%

    No Known Activations