© 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. 12715
    Prev
    Next
    INDEX
    Explanations

    advice and recommendations

    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
    æ·ŀ
    -0.22
    å¹²èĦĨ
    -0.21
    Ñįм
    -0.20
    ÑĤÑĥ
    -0.20
    hall
    -0.20
    æīĢ以ä»ĸ
    -0.19
     vess
    -0.19
    æ²ı
    -0.18
    åĮĻ
    -0.18
    /exp
    -0.18
    POSITIVE LOGITS
    åIJ¦åĪĻ
    0.24
    ä¸įçĦ¶
    0.23
     otherwise
    0.22
    è¿Ļæł·æīįèĥ½
    0.21
     ведÑĮ
    0.21
    otherwise
    0.20
    rier
    0.20
    åIJ¦åīĩ
    0.20
    æīįèĥ½
    0.19
    éĤ£æł·
    0.19
    Activations Density 0.136%

    No Known Activations