© 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
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 13475
    Prev
    Next
    INDEX
    Explanations

    weather and body conditions

    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
    人们çļĦ
    -0.22
    å·¥ä½ľçļĦ
    -0.20
    们çļĦ
    -0.19
    åIJĦèĩªçļĦ
    -0.19
    å¹¶ä¸įæĦıåij³
    -0.18
    å±Ĥåĩºä¸į
    -0.18
    ç»Ļ人ä¸Ģç§į
    -0.18
    åĪ©äºİ
    -0.18
    åħ¶å®ĥéĹ®é¢ĺ
    -0.17
    eltas
    -0.17
    POSITIVE LOGITS
    çªģ
    0.23
    å·²
    0.22
    èϽ
    0.21
    æ±Ł
    0.20
    ä¼¼ä¹İ
    0.20
    éĤł
    0.20
    åıĪ
    0.19
    亦
    0.19
    ä¹Ł
    0.19
    ä¹ŁåĽłæŃ¤
    0.19
    Activations Density 0.217%

    No Known Activations