© 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. 13161
    Prev
    Next
    INDEX
    Explanations

    personal context or requests

    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
     preload
    -0.21
    رÙĬÙħ
    -0.20
    å®īçĦ¶
    -0.20
     اÙĦأعÙħاÙĦ
    -0.19
    ford
    -0.19
    ä¸ĵä¸ļ人士
    -0.19
    ãģ¨ãģĦãģĨãĤĤãģ®
    -0.19
    æ¶İ
    -0.19
    æ²Ķ
    -0.19
    èĩ¾
    -0.19
    POSITIVE LOGITS
    /person
    0.22
     personally
    0.21
    åıĹ害èĢħ
    0.20
     indictment
    0.19
    å±ĤéĿ¢
    0.18
     scope
    0.18
    xes
    0.18
     individual
    0.18
     phạm
    0.17
     unins
    0.17
    Activations Density 0.012%

    No Known Activations