© 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. 13951
    Prev
    Next
    INDEX
    Explanations

    artist and installation

    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
    éĢļçķħ
    -0.21
    èĩªè´Ł
    -0.20
    abama
    -0.20
    اÙĤÙĦ
    -0.20
    rait
    -0.20
    elon
    -0.20
    acie
    -0.20
    lasses
    -0.20
    ä¼ĺè¶Ĭ
    -0.19
    é«ĺç´łè´¨
    -0.19
    POSITIVE LOGITS
    ä½ľåĵģ
    0.32
    åĪĽä½ľ
    0.28
    å±ķåĩº
    0.25
    å±ķè§Ī
    0.24
     artist
    0.24
    主é¢ĺ
    0.24
     space
    0.24
    è£ħç½®
    0.23
    å½¢å¼ı
    0.23
    å±ķ
    0.23
    Activations Density 0.062%

    No Known Activations