© 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. 11389
    Prev
    Next
    INDEX
    Explanations

    vaccine design and development

    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
    rees
    -0.24
    ness
    -0.19
    entication
    -0.18
    akk
    -0.18
     Mint
    -0.18
    ths
    -0.17
    ots
    -0.17
    uka
    -0.17
    rooms
    -0.17
    ened
    -0.17
    POSITIVE LOGITS
    ä¾£
    0.21
    iro
    0.20
    åĿĬ
    0.20
    artin
    0.18
    ural
    0.17
    urd
    0.17
    ivre
    0.17
    ع
    0.16
    fy
    0.16
    _accessible
    0.16
    Activations Density 0.005%

    No Known Activations