© 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. 12672
    Prev
    Next
    INDEX
    Explanations

    http/https links

    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
    Orm
    -0.21
    udos
    -0.19
    inent
    -0.19
    indy
    -0.19
    è¿ĺæľīä»Ģä¹Ī
    -0.19
    åĪĥ
    -0.18
    ending
    -0.18
    çīĮåŃIJ
    -0.18
    indo
    -0.18
    大åıĶ
    -0.17
    POSITIVE LOGITS
    çĪ°
    0.20
    åıijæĸĩ
    0.19
    éªĪ
    0.18
    ãĤ¸ãĤ§
    0.18
    PATCH
    0.18
    ç§ģç«ĭ
    0.18
    ä¸ĵ享
    0.17
    èĥģ
    0.17
     Fowler
    0.17
     marshal
    0.17
    Activations Density 0.036%

    No Known Activations