© 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. 14630
    Prev
    Next
    INDEX
    Explanations

    writable drive or disc

    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
    缺å¸Ń
    -0.20
    ä¸ĭ鼨
    -0.19
    nda
    -0.19
    yms
    -0.19
    å½Ģ
    -0.18
    æĭ±
    -0.18
    çĮ®
    -0.18
    æ¯ı人
    -0.18
    pill
    -0.18
     decltype
    -0.18
    POSITIVE LOGITS
    åĨī
    0.20
    èĩªå¦Ĥ
    0.19
    磨
    0.19
    cycle
    0.19
    é»ijçĻ½
    0.19
    è¹ī
    0.19
    åĨįçĶŁ
    0.19
    æľºåĪ¶
    0.19
    åİ¿åŁİ
    0.19
     princ
    0.19
    Activations Density 0.005%

    No Known Activations