© 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
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12448
    Prev
    Next
    INDEX
    Explanations

    degrees Celsius or Fahrenheit

    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
     Portions
    -0.18
    orial
    -0.18
    ä»»æĢ§
    -0.18
    ematic
    -0.18
    å¾Ĺèµ·
    -0.17
    MMdd
    -0.17
    ellaneous
    -0.17
    åĭĥåĭĥ
    -0.17
    ç¦ıå¾·
    -0.17
    _TI
    -0.16
    POSITIVE LOGITS
     Celsius
    0.25
    ally
    0.22
    ÙĬات
    0.18
    ä¸įåIJĮçļĦ
    0.18
    Mess
    0.17
    hk
    0.17
    ãĢħ
    0.17
    æľīåIJįçļĦ
    0.16
    ately
    0.16
    ois
    0.16
    Activations Density 0.022%

    No Known Activations