© 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. 13514
    Prev
    Next
    INDEX
    Explanations

    make selection or purchase

    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
    ï¸ı
    -0.18
    lando
    -0.18
    çŃĸ
    -0.17
    renc
    -0.17
    æ¼Ķ
    -0.16
     mere
    -0.16
     nil
    -0.16
     apex
    -0.16
    æĸ°åĬ¨èĥ½
    -0.16
     nad
    -0.16
    POSITIVE LOGITS
    leine
    0.26
     sure
    0.24
     strides
    0.24
    ioned
    0.23
    hift
    0.20
    (chan
    0.20
     educated
    0.20
    icing
    0.19
     acquaintance
    0.19
    -bel
    0.19
    Activations Density 0.203%

    No Known Activations