© 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. 11010
    Prev
    Next
    INDEX
    Explanations

    quoted text delimiters

    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
    ed
    -0.28
    er
    -0.25
    à¸Ļ
    -0.22
    ers
    -0.22
    al
    -0.20
    esco
    -0.20
    es
    -0.19
    åıįæŃ£
    -0.18
    ÑĢ
    -0.18
    edBy
    -0.18
    POSITIVE LOGITS
    ORY
    0.22
    sert
    0.20
    gunakan
    0.18
    URY
    0.18
    lü
    0.18
    istration
    0.17
    cle
    0.17
    vents
    0.17
    ean
    0.17
    ILT
    0.16
    Activations Density 0.036%

    No Known Activations