© 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. 12998
    Prev
    Next
    INDEX
    Explanations

    closest

    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
    åģľå·¥
    -0.21
     Scient
    -0.20
    æī¶è´«å·¥ä½ľ
    -0.20
     дов
    -0.19
    æıIJè´¨
    -0.19
     Kits
    -0.19
    çĽijè§Ĩ
    -0.19
    åĵij
    -0.19
     Chill
    -0.18
    转åIJij
    -0.18
    POSITIVE LOGITS
     closest
    0.24
    closest
    0.22
    è¢ĸ
    0.20
    è§Ĥ
    0.19
    èĤ´
    0.19
    /ap
    0.19
    å°Ĭ
    0.19
     Exactly
    0.19
    ä¹Łä¸įåı¯èĥ½
    0.18
    uga
    0.18
    Activations Density 0.353%

    No Known Activations