© 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. 10784
    Prev
    Next
    INDEX
    Explanations

    this source code

    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
    以为
    -0.20
    建
    -0.19
    iker
    -0.18
    åįı
    -0.18
    ise
    -0.18
    amed
    -0.18
    alking
    -0.17
     following
    -0.17
    ighthouse
    -0.17
    redi
    -0.17
    POSITIVE LOGITS
     {}:
    0.21
    æŃ£å¼ıåIJ¯åĬ¨
    0.20
    ç®Ģ缴æĺ¯
    0.20
     którego
    0.20
    æī¹æ¬¡
    0.20
    çĶŁæĢķ
    0.19
    çļĦåĬ¨åĬĽ
    0.19
    楼å±Ĥ
    0.19
    çħŀ
    0.18
    matter
    0.18
    Activations Density 0.011%

    No Known Activations