© 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. 15988
    Prev
    Next
    INDEX
    Explanations

    home care services

    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
    纬
    -0.22
    ä¸ĩåįĥ
    -0.20
    èįīæ¡Ī
    -0.20
    ATIC
    -0.19
     dim
    -0.19
     tast
    -0.18
    稳
    -0.18
    ï¸
    -0.18
    und
    -0.17
    ød
    -0.17
    POSITIVE LOGITS
    ä¸Ģ群
    0.20
    ä¸ĢåĽ¢
    0.20
    uber
    0.20
     Hamp
    0.19
    ä¸ĢåĪĨ
    0.19
    è·Łè¸ª
    0.18
    åĺ±
    0.18
    avail
    0.17
    éĴ©
    0.17
    ä¸Ģ对
    0.17
    Activations Density 0.009%

    No Known Activations