© 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. 15876
    Prev
    Next
    INDEX
    Explanations

    try catch except blocks

    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
    åľ¨è¿Ļç§į
    -0.20
    ç»ŃèĪª
    -0.18
    æķ²
    -0.18
    缴è¾ĸå¸Ĥ
    -0.18
    ylie
    -0.18
    èĬĤ课
    -0.17
    è¿Ļå°±
    -0.17
    æĨİ
    -0.17
     ÑħозÑı
    -0.17
    CRET
    -0.17
    POSITIVE LOGITS
    åį«çĶŁåģ¥åº·
    0.21
    ãģªãģijãĤĮãģ°
    0.20
    uala
    0.20
    ruc
    0.20
    çİĩ为
    0.19
    ÙĤÙĨ
    0.19
    culator
    0.19
    pty
    0.18
     наÑĢко
    0.18
    åħ¥çĿ¡
    0.18
    Activations Density 0.385%

    No Known Activations