© 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. 12885
    Prev
    Next
    INDEX
    Explanations

    bought it or liked it

    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
    zel
    -0.20
    ona
    -0.19
     grav
    -0.18
    举éĥ¨
    -0.17
     Vet
    -0.17
    æŀ·
    -0.17
    æĸ¹åľĨ
    -0.17
    åĩºäºĨ
    -0.17
    cut
    -0.17
    /forms
    -0.17
    POSITIVE LOGITS
    çĽĹ
    0.20
     bytearray
    0.20
     Affero
    0.19
    ä¹ĭåIJİ
    0.19
    å½¼
    0.19
    otch
    0.19
    çļĦæĦıè§ģ
    0.19
    类似
    0.19
    æ¤Ĵ
    0.19
    æĥ¨
    0.19
    Activations Density 0.011%

    No Known Activations