© 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. 13632
    Prev
    Next
    INDEX
    Explanations

    complex undertaking that requires

    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
    ä»ĸä»¬åľ¨
    -0.20
    å¾Ī满æĦı
    -0.19
    ifest
    -0.19
    éĹªéĹª
    -0.19
     Dispatch
    -0.19
    æĮºå¥½
    -0.19
    æĺ¯çĶ¨æĿ¥
    -0.18
    .chars
    -0.18
    ä¸į管
    -0.18
    ãģĬãģĭãģĴ
    -0.18
    POSITIVE LOGITS
     requires
    0.43
     ÑĤÑĢеб
    0.41
    éľĢè¦ģ
    0.39
     require
    0.38
    Requires
    0.37
     Requires
    0.36
    éĥ½éľĢè¦ģ
    0.36
    requires
    0.36
     requiring
    0.35
    æīĢéľĢ
    0.34
    Activations Density 0.168%

    No Known Activations