© 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. 15764
    Prev
    Next
    INDEX
    Explanations

    awkward and difficult to use

    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
    ä¹ĸä¹ĸ
    -0.20
    ellas
    -0.20
    襻
    -0.19
    家ä½ı
    -0.19
    çĪ±ç¾İ
    -0.18
    åĶ±æŃĮ
    -0.18
    ä¸įçĽ¸ä¿¡
    -0.18
    ëĿ¼ë©´
    -0.18
    è¿Ļå¼ł
    -0.18
    çĿij
    -0.18
    POSITIVE LOGITS
    æĭĻ
    0.33
    笨
    0.24
     manner
    0.24
    ä¸įåłª
    0.23
    çĶļèĩ³
    0.22
    è¸ī
    0.20
    çªł
    0.20
    appy
    0.20
    ä¸ĢåĽ¢
    0.20
     mat
    0.20
    Activations Density 0.032%

    No Known Activations