© 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
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 12220
    Prev
    Next
    INDEX
    Explanations

    in health

    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
    åħ¶å®ĥéĹ®é¢ĺ
    -0.25
    对äºİæĪij们
    -0.25
    è¿Ļä¹Īä¹ħ
    -0.24
    ãĥijãĥijæ´»
    -0.21
    åħ¶ä»ĸçݩ家
    -0.21
    åĮĹ京æĹ¶éĹ´
    -0.21
    è¿Ľä¸ĢæŃ¥
    -0.21
     weitere
    -0.20
    ä»Ĭ天å°ıç¼ĸ
    -0.20
    åį³å°ĨåΰæĿ¥
    -0.20
    POSITIVE LOGITS
    eren
    0.22
    æ»´
    0.21
    æŁIJ
    0.21
    ä¸ĢåIJį
    0.21
     "
    0.21
    a
    0.21
     “
    0.21
    *
    0.20
    tr
    0.20
     lump
    0.20
    Activations Density 0.275%

    No Known Activations