© 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. 14002
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    Desk
    -0.20
    icha
    -0.20
    æĶ¶åĽŀ
    -0.19
    æ¾į
    -0.17
    marshal
    -0.17
    .removeAll
    -0.17
    Levels
    -0.17
    Remarks
    -0.17
     INCLUDED
    -0.17
    éĻĶ
    -0.17
    POSITIVE LOGITS
    ersen
    0.20
    ä¸į认è¯Ĩ
    0.20
     Ames
    0.19
    orne
    0.18
    涧
    0.18
    èµı
    0.18
    ä½İ温
    0.18
    æĪij
    0.17
    åIJĦéĥ¨éŨ
    0.17
    ä¸Ģåı¥è¯Ŀ
    0.17
    Activations Density 0.006%

    No Known Activations