© 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. 13226
    Prev
    Next
    INDEX
    Explanations

    locations names and numbers

    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
    éĻĦ
    -0.21
    åľ°ä¸Ń
    -0.20
    éĢĶä¸Ń
    -0.20
    æľį
    -0.20
    å¤
    -0.19
    æĹģ
    -0.19
    REG
    -0.19
     Alf
    -0.18
    hq
    -0.18
    TypeInfo
    -0.18
    POSITIVE LOGITS
    ä¹ĭåīįçļĦ
    0.27
    ä¹ĭåIJİ
    0.24
    éĺĪ
    0.23
    å¼Ģå§ĭäºĨ
    0.22
    ä¹ĭåīį
    0.20
    å°ıäºİ
    0.20
    æѤåIJİ
    0.20
    è¿Ħ
    0.20
    临
    0.20
    çĪ»
    0.20
    Activations Density 0.235%

    No Known Activations