© 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. 12916
    Prev
    Next
    INDEX
    Explanations

    host cell lines

    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
     ze
    -0.22
    _MO
    -0.19
    ABCDE
    -0.19
     Pan
    -0.18
    неÑĨ
    -0.17
     zen
    -0.17
    MainThread
    -0.17
    çļĦæĸ¹å¼ıæĿ¥
    -0.17
    .quote
    -0.16
    azzi
    -0.16
    POSITIVE LOGITS
     Slot
    0.20
    egrity
    0.20
    nameof
    0.19
    infile
    0.19
    èĦ±åıij
    0.18
     SITE
    0.18
     Heads
    0.18
    ç´§
    0.18
    åħ±è¯Ĩ
    0.18
     Head
    0.18
    Activations Density 0.610%

    No Known Activations