© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10422
    Prev
    Next
    INDEX
    Explanations

    Salt Lake City / England

    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
    Negative Logits
    ient
    -0.21
    afa
    -0.21
    ernes
    -0.21
    æķĿ
    -0.19
    PLICIT
    -0.19
    .tk
    -0.18
    æľĢåIJİä¸Ģ次
    -0.18
    èĶ½
    -0.18
    ibraries
    -0.18
    ache
    -0.17
    POSITIVE LOGITS
    ]int
    0.19
    è¡«
    0.18
    ç®Ģæĺĵ
    0.17
    åħ¬ç½ijå®īå¤ĩ
    0.17
     zeroes
    0.17
    åIJįåĪĹåīį
    0.17
    éĿ©
    0.16
    pedia
    0.16
    >Main
    0.16
    æ³ķæ¡Ī
    0.16
    Activations Density 0.004%

    No Known Activations