© 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. 16472
    Prev
    Next
    INDEX
    Explanations

    alkyl or ethyl amine/amide

    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
    /reference
    -0.21
    å±ħ
    -0.20
    å¥Ĺ
    -0.20
     reference
    -0.20
    åĪĹ
    -0.20
    ä¸įåĪ°
    -0.19
    åºĶä»ĺ
    -0.19
    -worthy
    -0.19
    ibold
    -0.18
    marsh
    -0.18
    POSITIVE LOGITS
    oton
    0.21
    æ¤įåħ¥
    0.20
    è°Į
    0.20
    ç¢ĩ
    0.20
    èĮİ
    0.19
    å¢ŀ设
    0.18
    å²ĺ
    0.18
    ORD
    0.18
    æĺıè¿·
    0.18
    etri
    0.18
    Activations Density 0.198%

    No Known Activations