© 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. 11615
    Prev
    Next
    INDEX
    Explanations

    unsigned int, char, or long

    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
    ted
    -0.19
    ocop
    -0.18
    é©¿
    -0.18
    ÑĥÑĪки
    -0.17
    ÑģÑĤи
    -0.16
    ntl
    -0.16
    è®·
    -0.16
    arus
    -0.16
    Ùij
    -0.16
     leash
    -0.16
    POSITIVE LOGITS
     Guinness
    0.20
    ----------------------------------------------------------------
    0.18
    æł·çļĦ
    0.17
    ibility
    0.17
    ably
    0.17
    Truthy
    0.17
    y
    0.16
    etti
    0.16
    erala
    0.16
    atures
    0.16
    Activations Density 0.003%

    No Known Activations