© 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. 11655
    Prev
    Next
    INDEX
    Explanations

    responsible practices and decision-making

    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
    ugh
    -0.20
    à¹Į
    -0.20
    lined
    -0.18
    tures
    -0.18
    POCH
    -0.18
    elin
    -0.18
    ieres
    -0.18
    rames
    -0.17
    enez
    -0.17
    olith
    -0.17
    POSITIVE LOGITS
    /un
    0.23
    ä¹ĭ举
    0.20
    -minded
    0.20
    /legal
    0.20
     practices
    0.19
     manner
    0.19
    æݪæĸ½
    0.19
    ай
    0.18
     steward
    0.18
    -looking
    0.18
    Activations Density 0.006%

    No Known Activations