© 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. 11035
    Prev
    Next
    INDEX
    Explanations

    esn.cl, osl, essensoft

    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
    иÑĪ
    -0.20
    structions
    -0.19
    zel
    -0.18
    åķ¸
    -0.18
    å¿łå®ŀ
    -0.17
    sters
    -0.17
    åĻİ
    -0.17
    ìĦĿ
    -0.17
    eras
    -0.17
    и
    -0.17
    POSITIVE LOGITS
    ftware
    0.29
    ãģ¦ãģıãĤĮ
    0.19
    ×
    0.17
    åIJĦæł·
    0.17
    RIPT
    0.17
    åīįæıIJæĺ¯
    0.17
    ively
    0.16
    udio
    0.16
    conde
    0.16
    ellaneous
    0.16
    Activations Density 2.068%

    No Known Activations