© 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. 15839
    Prev
    Next
    INDEX
    Explanations

    visit

    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
    èĭ¦èĭ¦
    -0.21
    åij¶
    -0.21
     Ebony
    -0.20
    åĿļ飧
    -0.20
    .tie
    -0.20
    raq
    -0.19
    æħ·
    -0.19
    使çĶ¨å¯¿åij½
    -0.18
    éĨ¢
    -0.18
     Garland
    -0.18
    POSITIVE LOGITS
    访
    0.33
    åįĬ天
    0.32
    visit
    0.30
    åģľçķĻ
    0.30
    éĢĽ
    0.30
    è´Ń票
    0.30
    å°±è¿ij
    0.30
     visit
    0.28
    游è§Ī
    0.28
    åıĤè§Ĥ
    0.28
    Activations Density 0.078%

    No Known Activations