© 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. 14497
    Prev
    Next
    INDEX
    Explanations

    positive reviews and experiences

    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
    ç«ĭãģ¦
    -0.22
    è¦ģç´§
    -0.21
    /sec
    -0.21
     Holden
    -0.20
    åī¯ä¸»ä»»
    -0.20
    è¯Ĩ
    -0.20
    å±Ģ
    -0.19
    desk
    -0.19
    imals
    -0.19
    å·ħå³°
    -0.19
    POSITIVE LOGITS
    æľįåĬ¡è´¨éĩı
    0.33
    åı£ç¢ij
    0.30
    ä¼ĺèī¯
    0.28
    好æĦŁ
    0.28
    èī¯å¥½
    0.27
    ä¿¡èªī
    0.27
    åį°è±¡
    0.26
    满æĦı
    0.26
    èī¯å¥½çļĦ
    0.26
    è¯Ħä»·
    0.25
    Activations Density 0.147%

    No Known Activations