© 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. 13536
    Prev
    Next
    INDEX
    Explanations

    ACM, ASF

    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
    积累äºĨ
    -0.24
    åľ°ä¸Ń
    -0.20
    åIJĥäºı
    -0.20
     Ips
    -0.20
    YO
    -0.19
     unloaded
    -0.19
    EGIN
    -0.19
    XHR
    -0.18
     repe
    -0.18
    bol
    -0.18
    POSITIVE LOGITS
    æ´ŀ
    0.19
    åįĩéĻį
    0.19
    appa
    0.18
    ournals
    0.18
    ç»ĵ
    0.18
    สà¸ĩ
    0.18
     Peb
    0.18
    确认
    0.18
    é¤IJ
    0.18
    éĦĤ
    0.17
    Activations Density 0.025%

    No Known Activations