© 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. 16332
    Prev
    Next
    INDEX
    Explanations

    Messiah or Messenger

    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
    side
    -0.21
    å¤ļåįĬ
    -0.19
    app
    -0.19
    人å¿ĥ
    -0.17
     splash
    -0.17
    æ·«
    -0.17
    star
    -0.17
    æīĢè°ĵ
    -0.17
     ret
    -0.17
    in
    -0.17
    POSITIVE LOGITS
    åĢĻéĢī人
    0.23
    们
    0.19
    .expect
    0.19
    EXPECT
    0.19
    ÑĦик
    0.18
    .strict
    0.18
    atical
    0.18
    éĥľ
    0.17
    è´Ŀå°Ķ
    0.17
    mlin
    0.17
    Activations Density 0.001%

    No Known Activations