© 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
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15015
    Prev
    Next
    INDEX
    Explanations

    theoretical models and approaches

    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
     SearchResult
    -0.23
    交éĢļå·¥åħ·
    -0.22
     eskort
    -0.22
    对åħ¶çľŁå®ŀ
    -0.22
    ÑĩиÑģлен
    -0.20
    Dataset
    -0.20
    สà¸ĸาà¸Ļ
    -0.20
    dataset
    -0.19
    ="_
    -0.19
    oba
    -0.19
    POSITIVE LOGITS
     theory
    0.33
     view
    0.30
    认为
    0.28
     model
    0.27
     approach
    0.25
     treat
    0.24
    çľĭå¾ħ
    0.23
    çļĦ说æ³ķ
    0.23
     Kern
    0.23
    çIJĨ论
    0.22
    Activations Density 0.125%

    No Known Activations