© 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. 16003
    Prev
    Next
    INDEX
    Explanations

    job descriptions

    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
    éĻįä»·
    -0.20
    oby
    -0.19
    夯
    -0.19
     Ùħض
    -0.19
    ä¸ĥåħ«
    -0.18
    éĢĢå¸Ĥ
    -0.18
    ç®±åŃIJ
    -0.18
    åĻİ
    -0.18
    äº
    -0.18
    consult
    -0.18
    POSITIVE LOGITS
    èģĮä½į
    0.34
    æĭĽåĭŁ
    0.27
    èĸªéħ¬
    0.27
    åºĶèģĺ
    0.25
    æĭĽèģĺ
    0.24
    éĿ¢è¯ķ
    0.24
    ä¸Ģç»ı
    0.24
     Responsibilities
    0.23
    isclosed
    0.23
    å²Ĺä½į
    0.23
    Activations Density 0.152%

    No Known Activations