© 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. 13622
    Prev
    Next
    INDEX
    Explanations

    testing and evaluation

    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
    olie
    -0.25
    itag
    -0.20
    posting
    -0.20
    poly
    -0.19
    craper
    -0.19
    å¯Įæ°ij
    -0.19
    æģŃæķ¬
    -0.19
    DCF
    -0.19
    æĪijåıªæĺ¯
    -0.19
    opol
    -0.18
    POSITIVE LOGITS
     testing
    0.50
    æµĭè¯ķ
    0.50
    testing
    0.45
    -testing
    0.38
    éªĮè¯ģ
    0.38
     Testing
    0.37
    Testing
    0.35
     ÑĤеÑģÑĤ
    0.34
    ĭè¯ķ
    0.33
     test
    0.33
    Activations Density 0.158%

    No Known Activations