© 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. 14846
    Prev
    Next
    INDEX
    Explanations

    research characteristics

    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
     Cum
    -0.22
    社ä¼ļ稳å®ļ
    -0.20
     Pot
    -0.18
    çļĦä¸Ģåijĺ
    -0.18
    é«ĺæķĪçļĦ
    -0.18
    æ¯ĶèµĽä¸Ń
    -0.18
     Diamond
    -0.18
    .bootstrapcdn
    -0.18
    éĩįè¦ģçļĦ
    -0.17
    åĪĨæŀIJå¸Ī
    -0.17
    POSITIVE LOGITS
    èĥ½åĬĽåĴĮ
    0.34
    æĸ¹å¼ı
    0.28
     size
    0.27
    次æķ°
    0.27
    èĮĥåĽ´
    0.27
    æŶéĹ´åĴĮ
    0.26
    çİĩ
    0.26
     characteristics
    0.26
    éĢŁåº¦
    0.26
    éĢ¡
    0.26
    Activations Density 0.802%

    No Known Activations