© 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. 12218
    Prev
    Next
    INDEX
    Explanations

    special features and purposes

    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
    sis
    -0.18
    rogen
    -0.17
    antine
    -0.17
    soever
    -0.16
    -pound
    -0.16
    uled
    -0.16
    æģĤ
    -0.16
    WARD
    -0.15
    ez
    -0.15
    shan
    -0.15
    POSITIVE LOGITS
    -purpose
    0.31
    ity
    0.30
    ities
    0.30
    ÃŃsimo
    0.23
    izations
    0.23
    ITY
    0.22
    -interest
    0.21
    izing
    0.20
    ties
    0.20
     biá»ĩt
    0.20
    Activations Density 0.037%

    No Known Activations