© 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. 13787
    Prev
    Next
    INDEX
    Explanations

    returned for

    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
    åĸĦ
    -0.21
    ató
    -0.20
    _Play
    -0.19
    é«ĺå±Ĥ次
    -0.19
    (DE
    -0.19
    cou
    -0.18
    ifact
    -0.18
     ÐĺгÑĢ
    -0.18
    åĻ¨åħ·
    -0.17
    çĽ²
    -0.17
    POSITIVE LOGITS
     ÑĤоже
    0.38
     likewise
    0.32
     ebenfalls
    0.30
    ä¹Łéļıä¹ĭ
    0.30
    缸åºĶ
    0.29
    éļıä¹ĭ
    0.27
    æĪijä¹Ł
    0.26
    ä¹Łæĺ¯å¦ĤæѤ
    0.26
    缸åºĶçļĦ
    0.26
    åIJĮæł·
    0.26
    Activations Density 0.257%

    No Known Activations