© 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. 15580
    Prev
    Next
    INDEX
    Explanations

    have or wants to

    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
    ä½Ĩæĺ¯å¦Ĥæŀľ
    -0.21
    snow
    -0.20
    FileSync
    -0.20
    åĽłä¸ºå¥¹
    -0.20
    宽æĿ¾
    -0.20
    åıŃ
    -0.19
    pig
    -0.19
    æµ·æĭĶ
    -0.19
     Arbitrary
    -0.19
    éĽª
    -0.19
    POSITIVE LOGITS
    ï¼Į请
    0.26
    æĦŁåħ´è¶£
    0.24
    æĪĸèĢħåħ¶ä»ĸ
    0.24
    ä¸į妨
    0.24
    æĦ¿æĦı
    0.24
    æĪĸåħ¶ä»ĸ
    0.23
    æĪĸèĢħ
    0.22
    ORTH
    0.22
     or
    0.21
     interested
    0.21
    Activations Density 0.042%

    No Known Activations