© 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. 13876
    Prev
    Next
    INDEX
    Explanations

    . followed by something

    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
    -pill
    -0.19
    æĭį
    -0.18
    åĽ½ç½ij
    -0.18
    ades
    -0.18
     alkal
    -0.18
    ScreenState
    -0.18
    íķ´
    -0.17
    çķ
    -0.17
     succeeding
    -0.17
    å§Ķ
    -0.17
    POSITIVE LOGITS
    éĩįè¦ģåİŁåĽł
    0.24
    åİŁåĽłä¹ĭä¸Ģ
    0.21
    -style
    0.20
    ç½ijç«Ļåľ°åĽ¾
    0.19
    å«¡
    0.19
    åħ±å»º
    0.19
    á»Ĩ
    0.18
    hell
    0.18
    åıĭæĥħ
    0.18
    æł·å¼ı
    0.18
    Activations Density 0.007%

    No Known Activations