© 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. 16875
    Prev
    Next
    INDEX
    Explanations

    doing something in advance

    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
    åį±æľº
    -0.22
    åį±
    -0.21
    çİ°çĬ¶
    -0.21
    æľ¬è´¨
    -0.20
     Chancellor
    -0.19
     Townsend
    -0.19
    æľ¬è´¨ä¸Ĭ
    -0.19
    è¾¹ç¼ĺ
    -0.18
     cis
    -0.18
     arc
    -0.18
    POSITIVE LOGITS
    åĬŁè¯¾
    0.24
     görÃ¼ÅŁ
    0.22
    åĩĨå¤ĩ好
    0.22
    æīįèĥ½
    0.20
    åĩĨå¤ĩ
    0.19
    _define
    0.19
     Svens
    0.19
    iet
    0.19
    åĪ¶å®ļ
    0.19
    以便
    0.19
    Activations Density 0.033%

    No Known Activations