© 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. 16811
    Prev
    Next
    INDEX
    Explanations

    entirely too

    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
    dale
    -0.20
    满
    -0.18
     Trident
    -0.18
    =-=-=-=-=-=-=-=-
    -0.16
     Ballard
    -0.16
    ðŁı»
    -0.16
    ulton
    -0.15
    hiba
    -0.15
    iec
    -0.15
    èĬĹ
    -0.15
    POSITIVE LOGITS
    OfWork
    0.19
    Ñİ
    0.17
    ers
    0.17
     vapor
    0.17
    udes
    0.16
    odox
    0.16
    ways
    0.16
    à¸Ļ
    0.16
    éķ
    0.16
    à¸Ļาม
    0.16
    Activations Density 0.005%

    No Known Activations