© 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. 16513
    Prev
    Next
    INDEX
    Explanations

    Kennedy and variations

    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
    ively
    -0.20
    ners
    -0.19
    ings
    -0.16
    ãģ£ãģįãĤĬ
    -0.16
    adows
    -0.16
    gli
    -0.16
    åĦ¿
    -0.16
    heets
    -0.16
    ake
    -0.16
    TING
    -0.16
    POSITIVE LOGITS
    abad
    0.20
    å°¼æĸ¯
    0.19
     pong
    0.18
    yla
    0.17
    -quarters
    0.15
    arb
    0.15
    çĤ¹å¤ļ
    0.15
    ulet
    0.15
    ลà¸Ńà¸ĩ
    0.15
    usk
    0.14
    Activations Density 0.006%

    No Known Activations