© 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. 15446
    Prev
    Next
    INDEX
    Explanations

    common word endings

    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
    éŃģ
    -0.19
    çĪµ
    -0.19
    å·¾
    -0.18
    inel
    -0.17
    imizer
    -0.17
    çģµéŃĤ
    -0.17
    or
    -0.17
    orph
    -0.17
    osl
    -0.17
    locations
    -0.16
    POSITIVE LOGITS
    iana
    0.23
    ÙĬات
    0.22
    odox
    0.19
    ously
    0.19
    ous
    0.19
    yyy
    0.18
    /aws
    0.18
    UDA
    0.18
    ahoma
    0.17
    pek
    0.17
    Activations Density 0.003%

    No Known Activations