© 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. 10815
    Prev
    Next
    INDEX
    Explanations

    actions and their context

    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
    åĪijäºĭæ¡Ī件
    -0.23
    太大
    -0.23
    éĥ½æĹłæ³ķ
    -0.21
    æ¯ı天éĥ½
    -0.20
    è¢Ħ
    -0.19
    ấu
    -0.19
    åģĩè£ħ
    -0.19
    巴士
    -0.19
    пп
    -0.19
    BUFF
    -0.19
    POSITIVE LOGITS
     despite
    0.24
     actions
    0.21
    æŁIJç§įç¨ĭ度
    0.21
    propri
    0.21
     controversial
    0.20
    åĩºå¤Ħ
    0.20
    èĢĮéĿŀ
    0.20
    ä¸Ģå®ļç¨ĭ度
    0.19
     Tight
    0.19
     Against
    0.19
    Activations Density 0.070%

    No Known Activations