© 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. 13417
    Prev
    Next
    INDEX
    Explanations

    words ending in -ment or -able

    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
    ä¸Ģ举
    -0.21
    æ¸ħæĸ°
    -0.21
    Ñģа
    -0.20
    åį±
    -0.20
    èIJ¥éĢł
    -0.20
    æºIJæºIJ
    -0.19
    京åŁİ
    -0.18
    è¶ĬæĿ¥è¶Ĭå°ij
    -0.18
     Nev
    -0.18
    TAB
    -0.18
    POSITIVE LOGITS
    ç»ĵå±Ģ
    0.28
    éģĹæĨ¾
    0.28
    Completion
    0.26
    æĨ¾
    0.26
     ending
    0.25
     completion
    0.25
    completion
    0.25
     endings
    0.24
    åľĨ满
    0.23
    é²ĭ
    0.22
    Activations Density 0.116%

    No Known Activations