© 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. 13556
    Prev
    Next
    INDEX
    Explanations

    describes action or state

    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
    建设åĴĮ
    -0.25
    管çIJĨåĴĮ
    -0.23
    åĴĮåıijå±ķ
    -0.23
    çIJĨ解åĴĮ
    -0.23
     and
    -0.22
    ç»ıéªĮåĴĮ
    -0.21
    åĴĮåľ°åĮº
    -0.20
    æĸĩåĮĸåĴĮ
    -0.20
    à¹ģละà¸ģาร
    -0.19
    èĥ½åĬĽåĴĮ
    -0.19
    POSITIVE LOGITS
    åĽłæѤ
    0.28
     accordingly
    0.28
    以æѤ
    0.27
    çĶ±æѤ
    0.25
    äºĨä¸įå°ij
    0.23
    æį®æѤ
    0.23
    为æѤ
    0.23
     therefore
    0.22
    rog
    0.22
     thereof
    0.22
    Activations Density 0.230%

    No Known Activations