© 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. 16231
    Prev
    Next
    INDEX
    Explanations

    names and technical terms

    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
    er
    -0.24
    ity
    -0.20
     же
    -0.19
    им
    -0.16
    IZER
    -0.16
    ../../../
    -0.16
    ging
    -0.15
    รà¸Ńย
    -0.15
    ize
    -0.15
    emploi
    -0.15
    POSITIVE LOGITS
    olib
    0.16
    mand
    0.16
    metics
    0.16
    htag
    0.16
    stice
    0.15
    ders
    0.15
    amental
    0.15
    第ä¸ĢæŃ¥
    0.15
    forth
    0.15
    à¸Ļà¹Ĥย
    0.15
    Activations Density 0.443%

    No Known Activations