© 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. 12759
    Prev
    Next
    INDEX
    Explanations

    generated 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
    iÄĻ
    -0.23
    elman
    -0.19
    _instances
    -0.18
    éĵ©
    -0.17
    å®ŀåľ°
    -0.17
    åĪ©çĶ¨æĤ¨çļĦ
    -0.17
    _STRUCT
    -0.17
    çľĦ
    -0.17
    éļĹ
    -0.17
    éĻ¤æѤ
    -0.17
    POSITIVE LOGITS
    解éĩĬ
    0.21
    aku
    0.20
    认
    0.19
    åıĤèĤ¡
    0.19
     dens
    0.18
    ä¸Ģ段
    0.18
    acket
    0.18
    ä¸įåģľ
    0.17
    ä¸Ģè¡Į
    0.17
    istics
    0.17
    Activations Density 0.002%

    No Known Activations