© 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. 13449
    Prev
    Next
    INDEX
    Explanations

    or choices

    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
    toolbox
    -0.21
    акÑģ
    -0.19
    cock
    -0.19
    æĮ½
    -0.18
    ras
    -0.18
    =set
    -0.18
    ä½Ĩä¹Ł
    -0.18
    诸å¦Ĥ
    -0.17
    å¾ķ
    -0.17
    ãģ§ãģĤãĤįãģĨ
    -0.17
    POSITIVE LOGITS
    ä¹ĭäºī
    0.30
    åīįèĢħ
    0.24
    åıĸåĨ³äºİ
    0.22
    æĬīæĭ©
    0.21
    éĥ½ä¸įèĥ½
    0.21
    åIJĦèĩªçļĦ
    0.21
    åIJĦèĩª
    0.20
    è¿Ļ个éĹ®é¢ĺ
    0.20
    xis
    0.20
    åĨ³å®ļ
    0.20
    Activations Density 0.097%

    No Known Activations