© 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. 13969
    Prev
    Next
    INDEX
    Explanations

    shower enclosures and tubs

    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
    umont
    -0.20
    Kim
    -0.19
    æľĿå»·
    -0.19
    otide
    -0.18
    çĪº
    -0.18
    åĴĮ社ä¼ļ
    -0.18
    fortune
    -0.17
    weekday
    -0.17
    .dtype
    -0.17
     Unsigned
    -0.17
    POSITIVE LOGITS
    å¬ĸ
    0.26
    åħ¥åı£
    0.21
    横
    0.20
    ä¸ĵåijĺ
    0.20
    CDF
    0.19
    ган
    0.19
    ein
    0.19
    å¡Į
    0.18
    æĪ¿
    0.18
    综åIJĪä½ĵ
    0.18
    Activations Density 0.005%

    No Known Activations