© 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. 16067
    Prev
    Next
    INDEX
    Explanations

    status quo

    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
    æĬĢå·§
    -0.20
    çİĩ为
    -0.19
    åı¯éĿłçļĦ
    -0.19
    æĺŁåħī
    -0.18
    ĸ
    -0.18
    交éĢļæŀ¢çº½
    -0.18
    singular
    -0.18
    æĤ£èĢħçļĦ
    -0.17
    åı¯éĿł
    -0.17
    声èªī
    -0.17
    POSITIVE LOGITS
     quo
    0.23
    isers
    0.20
     ante
    0.20
    绽
    0.20
     лиÑĨ
    0.19
     operating
    0.19
    .statusText
    0.18
    .party
    0.18
     justice
    0.18
    秩åºı
    0.18
    Activations Density 0.021%

    No Known Activations