© 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. 14125
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ly' or 'y'

    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
    sWith
    -0.30
    ally
    -0.28
    nya
    -0.26
    ened
    -0.25
    ste
    -0.22
    ni
    -0.22
    ians
    -0.21
    nit
    -0.21
    ned
    -0.20
    ness
    -0.20
    POSITIVE LOGITS
    esterday
    0.32
    ields
    0.31
    outube
    0.30
    town
    0.28
    ramid
    0.27
    ielding
    0.27
    yyyy
    0.25
    osemite
    0.24
    tics
    0.24
    andex
    0.24
    Activations Density 1.301%

    No Known Activations