© 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. 14883
    Prev
    Next
    INDEX
    Explanations

    media and publications

    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
    ãĥªãĥ³
    -0.20
    çªĴ
    -0.20
     поÑĢÑıд
    -0.20
    azor
    -0.20
    åįĥéĩĮ
    -0.18
     влад
    -0.18
    ãĥijãĥijæ´»
    -0.18
     Outline
    -0.18
    使çĶ¨ç¶²è·¯
    -0.18
    äºĨä¸Ģåı£
    -0.18
    POSITIVE LOGITS
    original
    0.23
    å½ĵæŶçļĦ
    0.22
    åİŁå§ĭ
    0.22
    åĴĮ个人
    0.22
    以åıĬåħ¶ä»ĸ
    0.22
     original
    0.22
    åİĨå¹´
    0.20
    æĭį
    0.20
    å½ĵæŶ
    0.20
    ÙĤÙĪ
    0.19
    Activations Density 0.128%

    No Known Activations