© 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. 10811
    Prev
    Next
    INDEX
    Explanations

    original author or associated documentation

    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
    opr
    -0.18
    ugi
    -0.18
     eg
    -0.18
     same
    -0.18
    Ľå»º
    -0.18
    xz
    -0.17
    odor
    -0.17
    ossil
    -0.17
    çĶ¨å·¥
    -0.17
    æĪIJè´¥
    -0.17
    POSITIVE LOGITS
    æħİ
    0.22
    纪å¾ĭ
    0.21
    ledge
    0.21
     bleach
    0.20
    å¼Ħå¾Ĺ
    0.19
    è§Ĥèµı
    0.18
    缴å±ŀ
    0.18
    åħĶ
    0.17
    PHA
    0.17
     Lamb
    0.17
    Activations Density 0.002%

    No Known Activations