© 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. 15824
    Prev
    Next
    INDEX
    Explanations

    making decisions or selections

    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
    isEnabled
    -0.19
    ãģ¦ãģĦ
    -0.19
    丰å¯Įå¤ļ彩
    -0.18
    ernel
    -0.18
    é«Ģ
    -0.18
    é¹ij
    -0.18
    imoto
    -0.18
    享çĶ¨
    -0.18
     beta
    -0.18
    /embed
    -0.18
    POSITIVE LOGITS
    éĢīæĭ©
    0.41
    çļĦéĢīæĭ©
    0.40
     вÑĭбоÑĢ
    0.35
     selections
    0.35
     selection
    0.31
     choice
    0.31
    éģ¸æĵĩ
    0.31
     wybór
    0.30
    åĨ³å®ļ
    0.30
    éĢīæĭ©äºĨ
    0.28
    Activations Density 0.070%

    No Known Activations