© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12283
    Prev
    Next
    INDEX
    Explanations

    RSVP or specific phrases

    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
     apparently
    -0.18
    æĸ¯
    -0.17
    /or
    -0.17
     Parkway
    -0.17
    arin
    -0.17
    梧
    -0.17
    urdy
    -0.16
    Ðĺ
    -0.16
    å¾ĹåĪĨ
    -0.16
    è¿ĽèĢĮ
    -0.16
    POSITIVE LOGITS
    说æĺ¯
    0.20
    phan
    0.19
    OwnProperty
    0.18
    ifies
    0.18
    ration
    0.17
    ifiable
    0.17
    าà¸Ļ
    0.17
    iasi
    0.17
    elda
    0.17
    ä¸ĵçıŃ
    0.16
    Activations Density 0.077%

    No Known Activations