© 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. 15551
    Prev
    Next
    INDEX
    Explanations

    effects and development

    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
    为äºĨ
    -0.20
    èį·
    -0.20
    _ENUM
    -0.19
    çĤºäºĨ
    -0.19
    æı®
    -0.19
    çİĩ为
    -0.19
    为ä½ķ
    -0.18
    åĽłä¸º
    -0.18
    åĩºäºİ
    -0.18
    为äºĨ让
    -0.18
    POSITIVE LOGITS
    æīĭ段
    0.21
     means
    0.20
    кÑĥп
    0.19
    ĥģ
    0.19
    æıŃ
    0.19
     borrowed
    0.18
    -sama
    0.18
    çľĭä»ĸ
    0.18
    аÑĢа
    0.18
     пÑĢоб
    0.17
    Activations Density 0.972%

    No Known Activations