© 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. 13103
    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
     comb
    -0.21
    çļ®
    -0.20
     Mits
    -0.20
    ky
    -0.20
    èĤł
    -0.20
    湫
    -0.19
     too
    -0.19
    滤
    -0.19
    æĭĽ
    -0.19
    ç»Ī身
    -0.19
    POSITIVE LOGITS
    éĴ°
    0.21
     Jacket
    0.20
    åĽ½åºĨ
    0.20
    hợ
    0.18
    æľįåĭĻæĪĸ
    0.18
    arto
    0.18
     safezone
    0.18
    lightbox
    0.18
    æľįåĬ¡å¹³åı°
    0.18
    åħħåĪĨåĪ©çĶ¨
    0.18
    Activations Density 0.021%

    No Known Activations