© 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. 10640
    Prev
    Next
    INDEX
    Explanations

    own versions of programs

    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
    éĨį
    -0.20
    _nth
    -0.19
    çŁ¢
    -0.19
    æģŃåĸľ
    -0.19
    _OCC
    -0.18
    .Hidden
    -0.18
    ä¸ºæł¸å¿ĥ
    -0.18
    _locator
    -0.18
    brace
    -0.18
    æĺŁçIJĥ
    -0.17
    POSITIVE LOGITS
     Og
    0.21
    çĭ¬æľīçļĦ
    0.20
    称
    0.19
    åĵģ
    0.19
     original
    0.19
     own
    0.19
    æĺ¯åĽ½åĨħ
    0.19
     superior
    0.19
     Own
    0.19
     coats
    0.19
    Activations Density 0.212%

    No Known Activations