© 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. 14393
    Prev
    Next
    INDEX
    Explanations

    Counter-revolution and threats

    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
    åŀĤ
    -0.19
    ifter
    -0.19
    صاد
    -0.18
    éļ¾åħį
    -0.18
    åIJĮä»ģ
    -0.18
    èĻIJ
    -0.17
    奸
    -0.17
    è¹Ń
    -0.17
     ÑģобÑģÑĤвенно
    -0.17
    å½ĵå¹´
    -0.17
    POSITIVE LOGITS
     deemed
    0.23
    zar
    0.23
    itecture
    0.22
     supposedly
    0.19
    ä¸ĩä¸Ģ
    0.19
    åªļ
    0.18
    æĨ¬
    0.18
     perceived
    0.18
    人身
    0.18
    æķĻèĤ²åŁ¹è®Ń
    0.18
    Activations Density 0.065%

    No Known Activations