© 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. 15493
    Prev
    Next
    INDEX
    Explanations

    sample rate, size, entropy

    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
    çĦ¶æĺ¯
    -0.24
    ãĤį
    -0.19
    enticator
    -0.18
    fully
    -0.18
    /right
    -0.17
    /she
    -0.17
    omore
    -0.17
    umbo
    -0.17
    entic
    -0.16
    entication
    -0.16
    POSITIVE LOGITS
    hood
    0.17
    atic
    0.17
    ivre
    0.17
    ác
    0.17
    oret
    0.16
     кÑĢови
    0.16
    лекÑĤ
    0.15
    oose
    0.15
    è´Łè´£åIJĮå¿Ĺ
    0.15
    累累
    0.14
    Activations Density 0.059%

    No Known Activations