© 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. 13045
    Prev
    Next
    INDEX
    Explanations

    joining groups and activities

    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
    æłī
    -0.21
    ä¸ŃåĽ½æĶ¿åºľ
    -0.20
    ä¸įåĪ©
    -0.19
    解æĶ¾
    -0.19
    å±Ī
    -0.19
     пÑĢогн
    -0.19
    羨
    -0.19
    岿
    -0.19
    ç»ĵç®Ĺ
    -0.19
    ë¡Ģ
    -0.19
    POSITIVE LOGITS
    ç¤¾åĽ¢
    0.35
    æĬ¥åIJį
    0.31
    çĪ±å¥½
    0.30
     membership
    0.28
    åıĤåĬł
    0.27
     participation
    0.26
    åıĤä¸İ
    0.26
    åħ´è¶£
    0.26
    vol
    0.26
     volunteer
    0.25
    Activations Density 0.179%

    No Known Activations