© 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. 12900
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    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
     ...↵↵
    -0.18
    ãĥ³ãĤ°
    -0.17
    chaft
    -0.17
    ä¹ĥèĩ³
    -0.16
    primitive
    -0.16
    ä¸ĢèĦļ
    -0.16
    æĹħéĢĶ
    -0.16
    è±ģ
    -0.15
    äºĨä¸Ģåľº
    -0.15
     âĢ¦↵↵
    -0.15
    POSITIVE LOGITS
    veau
    0.20
    orst
    0.19
    thought
    0.18
    rens
    0.18
    åIJĮæľŁ
    0.17
    gram
    0.17
    ibrate
    0.17
    ogy
    0.17
    CKET
    0.17
     wards
    0.17
    Activations Density 0.100%

    No Known Activations