© 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. 12987
    Prev
    Next
    INDEX
    Explanations

    charitable organizations

    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
    榷
    -0.22
    å°ĸ
    -0.20
    æĬ¼
    -0.20
    çĪ¶åŃIJ
    -0.20
    éĶIJ
    -0.19
    çĽ²
    -0.19
    缩çŁŃ
    -0.18
    亲åŃIJ
    -0.18
    emann
    -0.18
    ereg
    -0.18
    POSITIVE LOGITS
    æľºæŀĦ
    0.21
    åľ¨æĪijåĽ½
    0.21
    æ³ķ人
    0.21
    illas
    0.21
     organizations
    0.20
    alah
    0.20
    èĢĺ
    0.20
    æĤĦæĤĦ
    0.19
    人人
    0.19
    å®ĹæŨ
    0.19
    Activations Density 0.018%

    No Known Activations