© 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. 13021
    Prev
    Next
    INDEX
    Explanations

    speech, bowel syndrome, prince, Lincoln, water

    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
    åĵı
    -0.22
    WindowState
    -0.20
    æīįèĥ½å¤Ł
    -0.20
    èģĶæĥ³
    -0.19
    åı¯æĥ³
    -0.19
    京津
    -0.19
    foil
    -0.19
    è§Ħç¨ĭ
    -0.19
     Boards
    -0.19
    éĥ½èĥ½å¤Ł
    -0.19
    POSITIVE LOGITS
    elor
    0.21
    éĩĮéĿ¢çļĦ
    0.21
    çĥ¦
    0.20
     Reb
    0.20
    顽
    0.20
    ugu
    0.20
    绵
    0.19
    湿
    0.19
    åıĽ
    0.19
    .defaultValue
    0.18
    Activations Density 0.001%

    No Known Activations