© 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. 15728
    Prev
    Next
    INDEX
    Explanations

    remove or delete

    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
     unfolding
    -0.20
    /watch
    -0.19
    ä¸įè¦ģ太
    -0.18
    说èĩªå·±
    -0.18
    æµĩ
    -0.18
    èĥĮçĿĢ
    -0.18
    abbrev
    -0.18
     viên
    -0.17
    ä¹°åĪ°
    -0.17
     ÑĢеж
    -0.17
    POSITIVE LOGITS
    åĪłéĻ¤
    0.25
    ลà¸ļ
    0.22
     delete
    0.21
    æł¸å®ŀ
    0.20
    /delete
    0.20
     remove
    0.20
    Remove
    0.20
     Remove
    0.20
    akes
    0.19
    æİ
    0.19
    Activations Density 0.015%

    No Known Activations