© 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. 12793
    Prev
    Next
    INDEX
    Explanations

    sense of

    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
    æľĢå¤ļçļĦ
    -0.18
    ä¸įåħ·å¤ĩ
    -0.18
    éĥ¨åĪĨåĨħ容
    -0.18
    èĨĿçĽĸ
    -0.17
    ä¸Ģç³»åĪĹ
    -0.17
    æ½Ń
    -0.17
     Terr
    -0.17
    é¹ī
    -0.16
    æį®è¯´
    -0.16
     пÑĢовед
    -0.16
    POSITIVE LOGITS
    使åij½æĦŁ
    0.29
    责任æĦŁ
    0.26
    紧迫
    0.23
     urgency
    0.22
     responsibility
    0.22
    thic
    0.22
    使åij½
    0.21
    Æ°u
    0.21
    sense
    0.20
    å½Ĵå±ŀ
    0.20
    Activations Density 0.009%

    No Known Activations