© 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. 11273
    Prev
    Next
    INDEX
    Explanations

    requirements, settings, or indications

    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
    çŃ¾ä¸ĭ
    -0.20
    åĬłå·¥åİĤ
    -0.20
    èĸĩ
    -0.20
    éŃħåĬĽ
    -0.20
    è¿Ľç¨ĭä¸Ń
    -0.19
     заÑĢ
    -0.18
    èĩªèº«çļĦ
    -0.18
    arer
    -0.18
     possibility
    -0.18
    åķĨæĬ¥
    -0.17
    POSITIVE LOGITS
     пÑĢиÑıÑĤн
    0.29
     ÐŁÐ¾Ñĩем
    0.28
     requirements
    0.27
     ÐĶмиÑĤÑĢ
    0.27
    åĪ¶åº¦
    0.27
    ÑĩÑĢежден
    0.26
     моÑīн
    0.26
    è§ĦåĪĻ
    0.26
     ÐIJлекÑģан
    0.26
    éĻIJåĪ¶
    0.25
    Activations Density 0.129%

    No Known Activations