© 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. 10972
    Prev
    Next
    INDEX
    Explanations

    anxiety and related disorders

    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
    VF
    -0.21
    hausen
    -0.20
    rylic
    -0.19
    rice
    -0.19
    $req
    -0.18
    产åĩº
    -0.18
    ãģ¥ãģıãĤĬ
    -0.18
     royalties
    -0.18
    manship
    -0.17
    ä¾ĽåºĶ
    -0.17
    POSITIVE LOGITS
     anxiety
    0.25
    çĦ¦èĻij
    0.25
    ä¸įå®ī
    0.23
     disorder
    0.22
     Anxiety
    0.22
    å¿ĥçIJĨ
    0.21
    æĥħ绪
    0.21
     nervous
    0.21
    丼
    0.20
    REA
    0.20
    Activations Density 0.024%

    No Known Activations