© 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. 12536
    Prev
    Next
    INDEX
    Explanations

    this followed by a noun

    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
    olarity
    -0.19
    imized
    -0.18
    Ñģкоп
    -0.17
    鹤
    -0.17
    çĽ²
    -0.17
     mil
    -0.17
    تÙģس
    -0.17
    éĢŀ
    -0.17
     иÑģÑĤ
    -0.17
    ationToken
    -0.16
    POSITIVE LOGITS
     are
    0.20
    éĥ½æĺ¯
    0.19
    çļĦçħ§çīĩ
    0.18
    主è¦ģæľī
    0.18
    enez
    0.18
    åIJĪä¸Ģ
    0.18
     Sisters
    0.17
    iles
    0.17
    大楼
    0.17
    ä¹Łéĥ½
    0.17
    Activations Density 0.076%

    No Known Activations