© 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. 12825
    Prev
    Next
    INDEX
    Explanations

    bring about, bring to, bring in

    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
     outgoing
    -0.17
    etrics
    -0.17
    blink
    -0.17
    assi
    -0.16
     respective
    -0.16
    apon
    -0.16
    Phones
    -0.16
    iped
    -0.15
    alent
    -0.15
    orgen
    -0.15
    POSITIVE LOGITS
    ToFront
    0.26
     together
    0.24
     forth
    0.24
    è¿ĩæĿ¥
    0.22
     внимание
    0.21
    ä¸Ģèµ·æĿ¥
    0.20
     ׾×Ļ×ĵ×Ļ
    0.20
    hurst
    0.19
    éģİä¾Ĩ
    0.19
     attention
    0.19
    Activations Density 0.064%

    No Known Activations