© 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. 13503
    Prev
    Next
    INDEX
    Explanations

    finished ninth

    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
    arte
    -0.20
    åĿĩ
    -0.19
    иÑĦ
    -0.19
     purse
    -0.19
    .GUI
    -0.18
     arte
    -0.18
     нам
    -0.18
     Cargo
    -0.18
    _GU
    -0.18
    .owl
    -0.18
    POSITIVE LOGITS
    ä¹Łå¸ĮæľĽ
    0.31
    ä¹ŁæĪIJ为
    0.30
    ä¹Łè¢«
    0.30
    ä¹ŁåĽłæѤ
    0.28
    ä¹Łå¼Ģå§ĭ
    0.28
    ä¹Łå¾Ī
    0.27
     also
    0.27
    ä¹Łéļıä¹ĭ
    0.27
    ä¹Łæ¯Ķè¾ĥ
    0.27
    ä¹ŁåºĶ该
    0.26
    Activations Density 0.376%

    No Known Activations