© 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. 14796
    Prev
    Next
    INDEX
    Explanations

    product reviews and local deals

    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
    merce
    -0.20
    /respond
    -0.19
    Audit
    -0.19
    ertime
    -0.19
     Audit
    -0.19
    -prefix
    -0.19
     auditing
    -0.18
    .operations
    -0.18
    urry
    -0.18
    utton
    -0.17
    POSITIVE LOGITS
     flash
    0.25
    æľĢæĸ°çļĦ
    0.25
    æľĢæĸ°
    0.24
    大åħ¨
    0.24
    åIJĦæĸ¹éĿ¢
    0.23
     latest
    0.22
     hakkında
    0.21
    çĥŃçĤ¹
    0.21
    è¦ģçĤ¹
    0.21
     articles
    0.21
    Activations Density 0.041%

    No Known Activations