© 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. 13039
    Prev
    Next
    INDEX
    Explanations

    embryonic development

    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
    绪
    -0.22
     lac
    -0.20
    ä¸Ģ个æĸ°çļĦ
    -0.19
    rement
    -0.18
    icia
    -0.18
    å¦Ĥæŀľä¸į
    -0.18
    æ©Ħæ¦Ħ
    -0.17
     Miz
    -0.17
    åľ¨å¤ĸéĿ¢
    -0.17
     onFailure
    -0.17
    POSITIVE LOGITS
    ä¾ij
    0.19
    meld
    0.19
    __,__
    0.18
    IBLE
    0.18
    æĺ§
    0.17
    oky
    0.17
     STATES
    0.17
    æĺİ亮
    0.17
    imore
    0.17
    fare
    0.17
    Activations Density 0.013%

    No Known Activations