© 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. 13052
    Prev
    Next
    INDEX
    Explanations

    coins and currencies

    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
     knull
    -0.23
    vangst
    -0.22
    ÑĢен
    -0.20
     arsch
    -0.20
    allery
    -0.19
    æ°Ķä½ĵ
    -0.19
    prowadzi
    -0.19
    npos
    -0.19
    нÑĮ
    -0.19
    æ²¹èĦĤ
    -0.18
    POSITIVE LOGITS
    æľīè¿ĩ
    0.20
    osphere
    0.19
    ifier
    0.19
    ry
    0.18
    åİ»åģļ
    0.18
     ram
    0.18
    cy
    0.17
    Pri
    0.17
     undert
    0.17
    ä¸Ģ大
    0.17
    Activations Density 0.592%

    No Known Activations