© 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. 15571
    Prev
    Next
    INDEX
    Explanations

    possessive or contraction apostrophe

    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
     ‘
    -0.18
    ed
    -0.17
    ãĤĭ
    -0.17
    çľ¼åīį
    -0.17
    afka
    -0.15
     ’
    -0.15
    iating
    -0.15
    ing
    -0.15
     ens
    -0.15
    essim
    -0.15
    POSITIVE LOGITS
    ally
    0.22
    åĦ¿
    0.17
    wards
    0.17
    unce
    0.16
    å§Ķç»Ħç»ĩéĥ¨
    0.16
    ALLY
    0.16
    天é¹ħ
    0.16
    çĸĻ
    0.16
    åħ±æĮ¯
    0.15
     ë¶Ī구íķĺê³ł
    0.15
    Activations Density 0.179%

    No Known Activations