© 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. 16914
    Prev
    Next
    INDEX
    Explanations

    first signs of damage

    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
    å®Į
    -0.23
    追
    -0.22
    å®ĮäºĨ
    -0.22
    å®ĮæĪIJ
    -0.20
    ãģ¾ãģ¨ãĤģ
    -0.20
    Completed
    -0.19
    -complete
    -0.19
    å®Įæķ´
    -0.19
    uen
    -0.19
     Completed
    -0.19
    POSITIVE LOGITS
    å¼Ģå§ĭ
    0.27
    å¼Ģå§ĭäºĨ
    0.25
    å·²ç»ıå¼Ģå§ĭ
    0.25
    第ä¸Ģ家
    0.24
    ãģ¯ãģĺ
    0.23
    ä¹Łå¼Ģå§ĭ
    0.23
     Begins
    0.23
    迹象
    0.23
    é¦ĸ
    0.22
    é¦ĸ家
    0.22
    Activations Density 0.253%

    No Known Activations