© 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. 14765
    Prev
    Next
    INDEX
    Explanations

    urls and community links

    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
    ç½ijåºĹ
    -0.23
     setter
    -0.23
     Setter
    -0.22
    DAQ
    -0.22
    (Expected
    -0.22
    åIJĪçIJĨ
    -0.20
    ãĦ§
    -0.20
    éĢIJ
    -0.19
    ä¿İ
    -0.19
    èijĹ
    -0.19
    POSITIVE LOGITS
    Workspace
    0.22
    æ»ł
    0.20
    éĵª
    0.20
    éĽ¢ãĤĮ
    0.19
    PlainText
    0.19
    ãĤ°ãĥ©
    0.19
    .opensource
    0.18
    .twimg
    0.18
     AMP
    0.18
    åıijå±ķ空éĹ´
    0.18
    Activations Density 0.046%

    No Known Activations