© 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. 14618
    Prev
    Next
    INDEX
    Explanations

    opening and unlocking

    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
    éĢĶ
    -0.20
    åijĹ
    -0.20
     Critical
    -0.20
    iffin
    -0.20
    ç»ĵæĿŁåIJİ
    -0.20
    ç³Ĭ
    -0.19
    æ´Ĺ
    -0.18
    绾
    -0.18
     cleanup
    -0.18
    cle
    -0.18
    POSITIVE LOGITS
    ë´ī
    0.20
    åĸĿäºĨ
    0.20
     оÑĤкÑĢ
    0.20
    ä¸ĭè¡Į
    0.20
    夺å¾Ĺ
    0.19
    ä¸ĩåIJ¨
    0.19
    accordion
    0.19
    extr
    0.18
    bird
    0.18
    æīĵå¼Ģ
    0.18
    Activations Density 0.016%

    No Known Activations