© 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. 10818
    Prev
    Next
    INDEX
    Explanations

    N-starting names and acronyms

    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
     noticeable
    -0.22
     notion
    -0.21
    NavItem
    -0.19
     nghiá»ĩm
    -0.18
     nationals
    -0.18
     nature
    -0.17
     notions
    -0.17
     noon
    -0.17
    nature
    -0.17
    -nav
    -0.17
    POSITIVE LOGITS
    ê¹IJ
    0.35
    theless
    0.27
    lify
    0.25
    utilus
    0.25
    IGATION
    0.22
    avigator
    0.21
    uyen
    0.21
    ç²¹
    0.20
    ptune
    0.19
    veau
    0.18
    Activations Density 2.810%

    No Known Activations