© 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. 14572
    Prev
    Next
    INDEX
    Explanations

    ports and connectors

    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
    ä¸Ńå¼ı
    -0.21
    rippling
    -0.20
     pii
    -0.20
     intens
    -0.20
     Hur
    -0.20
    éĽª
    -0.20
    æ¢Ń
    -0.19
    å±ĭ顶
    -0.19
    (filters
    -0.19
    å½¹
    -0.19
    POSITIVE LOGITS
    -slot
    0.23
     ports
    0.22
    æīģ
    0.20
    ä¸įåıĺ
    0.20
    _PORTS
    0.20
    slot
    0.19
     Ports
    0.19
    尺寸
    0.19
    less
    0.19
     Sized
    0.19
    Activations Density 0.036%

    No Known Activations