© 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. 14732
    Prev
    Next
    INDEX
    Explanations

    certification and training qualifications

    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
    å¹¼ç¨ļ
    -0.23
    æī¾åĩĨ
    -0.23
    _tel
    -0.20
    è¸Ĭ
    -0.20
    æ¯įæł¡
    -0.20
    èīºæľ¯åĵģ
    -0.19
    ä¸Ĭå¹´åIJĮæľŁ
    -0.19
    åľ£è¯ŀ
    -0.19
     glad
    -0.19
    æ¥
    -0.18
    POSITIVE LOGITS
    è¯ģ书
    0.26
    åŁ¹è®Ń
    0.25
    åŁ¹è®ŃçıŃ
    0.24
    venience
    0.23
    okit
    0.20
     trainer
    0.20
    讲å¸Ī
    0.20
    ocop
    0.20
    certificate
    0.19
    课ç¨ĭ
    0.19
    Activations Density 0.016%

    No Known Activations