© 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. 16598
    Prev
    Next
    INDEX
    Explanations

    articles followed by nouns or requests

    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
    ç»ĻäºĨæĪij
    -0.22
    åİŁæľī
    -0.20
     ÑĢанее
    -0.20
    å·²æľī
    -0.19
    æĥ³çĿĢ
    -0.19
    趺
    -0.19
    æħµ
    -0.19
    å²Į
    -0.18
    enus
    -0.18
    æľºæ²¹
    -0.18
    POSITIVE LOGITS
    èĥ½
    0.23
     desperately
    0.23
     help
    0.23
    çIJĨçĶ±
    0.23
     to
    0.22
    lessly
    0.21
    èĥ½åľ¨
    0.20
    å¼ķ
    0.20
     badly
    0.19
    缴
    0.19
    Activations Density 0.148%

    No Known Activations