© 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. 12425
    Prev
    Next
    INDEX
    Explanations

    should have received

    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
    ä½ĵåĪ¶æĶ¹éĿ©
    -0.20
    对äºİæĪij们
    -0.18
    æīĢè°ĵ
    -0.18
    æĪijè¿ĺæĺ¯
    -0.17
    æĪij们çİ°åľ¨
    -0.17
    ä»Ģä¹Īåı«
    -0.17
    è¿Ļæīį
    -0.17
    ä¹ĭæīĢ以
    -0.17
    åŃIJéĩĮ
    -0.16
    åĪ¶å®ļäºĨ
    -0.16
    POSITIVE LOGITS
    /w
    0.29
    ered
    0.25
    /is
    0.25
     be
    0.23
    nt
    0.23
     бÑĭÑĤÑĮ
    0.22
    /c
    0.22
    /do
    0.21
    ering
    0.21
    åģļçļĦäºĭ
    0.20
    Activations Density 0.069%

    No Known Activations