© 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. 13011
    Prev
    Next
    INDEX
    Explanations

    circulating

    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
    éªħ
    -0.19
    hood
    -0.18
    é½
    -0.17
    ãģĦãģĨ
    -0.16
    ongs
    -0.16
    ëĭ¹
    -0.16
    falls
    -0.16
    à¹Ģà¸Ńา
    -0.15
    imon
    -0.15
    ãĤ¦ãĤ©
    -0.15
    POSITIVE LOGITS
    ally
    0.19
     kiá»ĩn
    0.18
    abouts
    0.17
    uard
    0.17
    çĿĢ
    0.17
    зов
    0.16
    ढ
    0.16
    us
    0.16
    encies
    0.16
    uild
    0.16
    Activations Density 0.022%

    No Known Activations