© 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. 12057
    Prev
    Next
    INDEX
    Explanations

    designation or status

    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
     пÑĢоб
    -0.23
    ç²¾åĬĽ
    -0.22
    è¿ĩåī©
    -0.20
    ç´¯äºĨ
    -0.19
    åħ´èĩ´
    -0.19
    onet
    -0.18
    èĩªå·±åĸľæ¬¢
    -0.18
    pes
    -0.18
    èĩ´åĬĽ
    -0.17
    åIJ¬äºĨ
    -0.17
    POSITIVE LOGITS
    身份
    0.28
    å°±æĦıåij³çĿĢ
    0.25
    åľ°ä½į
    0.23
    æĦıåij³çĿĢ
    0.23
    å¾ħéģĩ
    0.23
    认å®ļ
    0.23
    hood
    0.22
     status
    0.21
    级åĪ«çļĦ
    0.21
    osis
    0.21
    Activations Density 0.078%

    No Known Activations