© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12409
    Prev
    Next
    INDEX
    Explanations

    PhD degree

    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
    edio
    -0.23
    eton
    -0.19
    deprecated
    -0.18
    keit
    -0.18
    edList
    -0.17
    ç¡ħè°·
    -0.17
    istic
    -0.17
    lijk
    -0.16
    éĢĤ度
    -0.16
    ivirus
    -0.16
    POSITIVE LOGITS
    ä¿Ł
    0.17
    /oct
    0.17
    ä¸ĢèĪ¬æĿ¥è¯´
    0.17
    å¾Ĵ
    0.16
    Rep
    0.16
    æĤī
    0.16
    omas
    0.16
    ðŁı¾
    0.16
    åIJİçļĦ
    0.16
    BERT
    0.16
    Activations Density 0.008%

    No Known Activations