© 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. 11595
    Prev
    Next
    INDEX
    Explanations

    date stamps with time

    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
     lanc
    -0.20
    çĽij
    -0.19
    tal
    -0.19
    arin
    -0.19
     Ashe
    -0.19
    eref
    -0.19
    ixin
    -0.19
    éļ½
    -0.18
    ä¿¡
    -0.18
    PK
    -0.18
    POSITIVE LOGITS
    å¤ľæĻļ
    0.21
    çĨ¬å¤ľ
    0.21
     nights
    0.20
    itter
    0.19
    cers
    0.19
    çĿ¡çľł
    0.19
    elaide
    0.19
    bers
    0.19
     Nights
    0.19
    leep
    0.18
    Activations Density 0.019%

    No Known Activations