© 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. 13211
    Prev
    Next
    INDEX
    Explanations

    offering or doing things for others

    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
    æķ¢äºİ
    -0.21
    é¢ģå¸ĥ
    -0.20
    对æĪij说
    -0.19
    å¤ļéĩį
    -0.19
    ptime
    -0.19
    对æĪij
    -0.18
    æľī没æľī
    -0.18
    ACT
    -0.18
     dara
    -0.18
    èµĭäºĪ
    -0.18
    POSITIVE LOGITS
     ado
    0.22
    å¸®ä½ł
    0.20
    :`~
    0.19
    èĢ½è¯¯
    0.19
    åIJįçīĩ
    0.19
     apa
    0.19
    åįıåĬ©
    0.18
    ãĥĻãĤ¹ãĥĪ
    0.18
    åģļèµ·
    0.18
    AnimationFrame
    0.18
    Activations Density 0.047%

    No Known Activations