© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 12277
    Prev
    Next
    INDEX
    Explanations

    Subject Id $ or given int The Empty ( :

    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
    .CommandType
    -0.30
    	iVar
    -0.27
    URLException
    -0.26
    .CommandText
    -0.26
    .getContentPane
    -0.25
    CppMethod
    -0.25
     incon
    -0.24
    .awt
    -0.23
    CppObject
    -0.23
    CppClass
    -0.23
    POSITIVE LOGITS
     наÑĢко
    0.51
     пÑĢиÑıÑĤн
    0.43
     меÑĢоп
    0.42
    -Semit
    0.41
     ÐIJлекÑģан
    0.41
     моÑīн
    0.41
     ÐŁÐ¾Ñĩем
    0.39
     поÑģколÑĮ
    0.39
     ÑĢÑĥков
    0.38
     подÑĢобн
    0.37
    Activations Density 3.699%

    No Known Activations