© 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. 14478
    Prev
    Next
    INDEX
    Explanations

    no wonder, not surprising

    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
    æľĢ好ä¸įè¦ģ
    -0.24
    ç»Ŀä¸į
    -0.20
    ipelines
    -0.19
    Visited
    -0.19
    ç»Ĩèħ»
    -0.18
    å°½åı¯èĥ½
    -0.18
    å®Įåħ¨åı¯ä»¥
    -0.18
    å¦Ĥæŀľä¸į
    -0.18
    ä¸Ģå®ļè¦ģ
    -0.18
    å°½éĩı
    -0.17
    POSITIVE LOGITS
    éļ¾æĢª
    0.38
    ÂĢÂ
    0.22
    alien
    0.22
    ãģ¨è¨Ģãģ£ãģ¦
    0.21
    rena
    0.21
    ÂĢÂĻ
    0.20
    çļĦç»ĵæŀľ
    0.20
    abet
    0.20
     lif
    0.20
    åŀĤ
    0.19
    Activations Density 0.014%

    No Known Activations