© 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. 10956
    Prev
    Next
    INDEX
    Explanations

    take off or remove

    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
     Trip
    -0.21
     trip
    -0.20
    ifu
    -0.20
    icy
    -0.19
    æ´»è·ĥ
    -0.19
    åIJĮä¸Ģ
    -0.19
    LOY
    -0.19
    çĭĻ
    -0.19
    ecute
    -0.18
    çķ¸
    -0.18
    POSITIVE LOGITS
    解å¼Ģ
    0.24
    åİ»æİī
    0.22
    removed
    0.21
     removed
    0.21
    (remove
    0.20
    .remove
    0.20
     remove
    0.20
    REMOVE
    0.20
    -remove
    0.20
    èĩ³æѤ
    0.19
    Activations Density 0.013%

    No Known Activations