© 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. 14219
    Prev
    Next
    INDEX
    Explanations

    Karma yoga

    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
    èģĮä¸ļéģĵå¾·
    -0.24
    Ex
    -0.23
    ç¼ĵç¼ĵ
    -0.23
    æĢ¼
    -0.22
    sc
    -0.22
    è¯
    -0.22
    大佬
    -0.21
    åºĶçĶ¨åľºæĻ¯
    -0.20
    Single
    -0.20
    po
    -0.20
    POSITIVE LOGITS
    VMLINUX
    0.30
    #aa
    0.26
    iated
    0.24
    CALLTYPE
    0.24
    põe
    0.24
    ÑĨа
    0.24
    vana
    0.23
    ÑĨе
    0.23
    dão
    0.22
    europäische
    0.22
    Activations Density 0.011%

    No Known Activations