© 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. 12828
    Prev
    Next
    INDEX
    Explanations

    quotes starting with certain letters

    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
    -0.25
    "
    -0.24
     pr
    -0.23
     something
    -0.22
     non
    -0.22
     "
    -0.21
     such
    -0.21
    .getContentPane
    -0.21
    ·»
    -0.21
     c
    -0.21
    POSITIVE LOGITS
    æĪ¿éĹ´éĩĮ
    0.22
    ç§Ģ丽
    0.20
    æĹłæĦı
    0.20
    åľ¨çĶŁæ´»ä¸Ń
    0.20
    åĩĮæĻ¨
    0.19
    强çĥĪçļĦ
    0.19
    é¥Ńèıľ
    0.19
    èģĴ
    0.18
    åļ´éĩį
    0.18
    å±ħçĦ¶
    0.18
    Activations Density 0.034%

    No Known Activations