© 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. 11295
    Prev
    Next
    INDEX
    Explanations

    Johnny followed by a last name

    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
    -vous
    -0.18
    anders
    -0.17
    onaut
    -0.16
    ète
    -0.15
    èļĵ
    -0.15
    绶
    -0.15
    pathname
    -0.15
     единÑģÑĤв
    -0.15
    cla
    -0.15
    pll
    -0.15
    POSITIVE LOGITS
    liner
    0.20
    Ñĥг
    0.19
    aneous
    0.18
    zelf
    0.17
    åħ¶ä»ĸ
    0.16
    iated
    0.16
     Gazette
    0.16
     sake
    0.16
    iros
    0.16
    isable
    0.15
    Activations Density 0.009%

    No Known Activations