© 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. 10747
    Prev
    Next
    INDEX
    Explanations

    excitotoxicity or broth

    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
    éĹ¼
    -0.23
    å»¶æľŁ
    -0.22
    æľŁéĻIJ
    -0.21
    æľīæľŁ
    -0.21
    miÅŁ
    -0.20
    æ¸ł
    -0.20
    ç¼ł
    -0.18
    ä¸Ģæīĭ
    -0.18
    åıĬæŶ
    -0.18
    çĻ½æ²Ļ
    -0.18
    POSITIVE LOGITS
    é£ķ
    0.18
     Helpful
    0.18
    liner
    0.17
    å¤ĸ交éĥ¨
    0.17
    éĢĢ
    0.17
    å¸Ĥ人大
    0.17
     [~,
    0.16
     lẽ
    0.16
    (Void
    0.16
    _HOOK
    0.16
    Activations Density 0.009%

    No Known Activations